Community
cancel
Showing results for 
Search instead for 
Did you mean: 
emregun
New Contributor I
1,327 Views

ssd_mobilenet_v1_fpn_shared_coco model: "detection_classes is not in graph" error

Requirements:

Python:3.7
MacOS:Big Sur 11.2.1
Openvino:openvino_2021.3.394
Tensorflow:1.14.0

Description:

When I try to create frozen model from my ssd_mobilenet_v1_fpn_shared_coco model(checkpoint, events.out.tfevents.1613600796.emres-air, graph.pbtxt, model.ckpt-90728.meta, model.ckpt-90728.index, and pipeline.config files), I am getting "detection_classes is not in graph" error, although I am using the same output nodes as defined in intel website.

 

Could someone tell me what I am doing wrong?

 

Thanks a lot in advance.

 

My steps:

1.I downloaded following model from intel website(and output nodes are also defined in this website):

 https://docs.openvinotoolkit.org/latest/omz_models_model_ssd_mobilenet_v1_coco.html

 

2.Custom trained it with following command with my own photos:
2.1 Code:
https://github.com/tensorflow/models
(master branch)
2.2 Command:
python3.7 train.py
--logtostderr
--train_dir=/Users/Documents/Temp/tensorflow_last/models/train
--pipeline_config_path=/Users/Documents/Temp/tensorflow_last/models/ssd_mobilenet_v1_fpn_shared_box_predictor_640x640_coco14_sync.config
Note:I can also attach my config file, if it is related
2.3 Output:
...
INFO:tensorflow:global step 89547: loss = 0.0628 (8.283 sec/step)
I0629 19:34:56.030186 4505345536 learning.py:512] global step 89547: loss = 0.0128 (8.283 sec/step)
INFO:tensorflow:global step 89548: loss = 0.0596 (9.801 sec/step)
I0629 19:35:05.831597 4505345536 learning.py:512] global step 89548: loss = 0.0196 (9.801 sec/step)
...

3.I tried to convert my files(checkpoint, events.out.tfevents.1613600796.emres-air, graph.pbtxt, model.ckpt-90728.meta, model.ckpt-90728.index, and pipeline.config files) to frozen model as described in following website:

3.1 Code: https://blog.metaflow.fr/tensorflow-how-to-freeze-a-model-and-serve-it-with-a-python-api-d4f3596b3ad...

Parameters:--model_dir
/Users/emre/Documents/Temp/tensorflow_last/models/train/
--output_node_names
detection_classes,detection_scores,detection_boxes,num_detections

3.2Output:At Line 51: (output_node_names.split(",")) I am getting following error message:
assert d in name_to_node, "%s is not in graph" % d
AssertionError: detection_classes is not in graph

 

Note:my expected output nodes are also not printed out in graph.pbtxt file. (please see attachment)

Best Regards

Emre

0 Kudos
23 Replies
Syamimi_Intel
Moderator
1,184 Views

Hi Emre Gun,

Thank you for reaching out. Seems like this is not our official website. You can have a try to freeze the ssd_mobilenet_v1_fpn_shared_coco model by using the following code:

import tensorflow as tf

from tensorflow.python.framework import graph_io

frozen = tf.graph_util.convert_variables_to_constants(sess, sess.graph_def, ["name_of_the_output_node"])

graph_io.write_graph(frozen, './', 'inference_graph.pb', as_text=False)

 

For more information, you can refer to Freezing Custom Models in Python*

 

 

Regards,

Syamimi


emregun
New Contributor I
1,175 Views

Hi Syamimi,

 

Thanks a lot for the response. Unfortunately the same error message:

assert d in name_to_node, "%s is not in graph" % d
AssertionError: detection_classes is not in graph

 

Do you have an other idea?

 

Best Regards

Emre

emregun
New Contributor I
1,149 Views

A correction:

The link in the first step above should be fixed:

1.I downloaded following model from intel website(and output nodes are also defined in this website):

 https://docs.openvinotoolkit.org/latest/omz_models_model_ssd_mobilenet_v1_coco.html

 

this above link should be corrected with following link(I used fpn_coco):

https://docs.openvinotoolkit.org/latest/omz_models_model_ssd_mobilenet_v1_fpn_coco.html

 

I am sorry for the mistake.

emregun
New Contributor I
1,141 Views

I would be grateful for another solutions? I am unfortunately stuck.
Syamimi_Intel
Moderator
1,134 Views

Hi Emre Gun,

I notice that you have graph.pbtxt. Thus, you can have a try to convert the model by using the following command:

python3 mo_tf.py --input_model <INFERENCE_GRAPH>.pbtxt --input_checkpoint <INPUT_CHECKPOINT> --input_model_is_text --output_dir <OUTPUT_MODEL_DIR>

 

You can refer to this model.yml file for your reference to your custom model.

For your information, this model.yml is validated by OpenVINO. And, you need to follow the topologies based on this documentation.

 

 

Regards,

Syamimi


emregun
New Contributor I
1,126 Views

Hi Syamimi,

Thanks for the response. It was really helpful. I had a look to the "Loading Non-Frozen Models to the Model Optimizer" description in intel website:

https://docs.openvinotoolkit.org/2021.1/openvino_docs_MO_DG_prepare_model_convert_model_Convert_Mode...

And I recognised that 2.MetaGraph is more suitable for my structure instead of 1.checkpoint, with the reason that I have just these files in my train folder:

  • model_name.meta
  • model_name.index
  • model_name.data-00000-of-00001

Unfortunately I do not have checkpoint_file.ckpt file in my train folder. Therefore I used following command to create my frozen model, but I got again a similar error as before about my nodes "Graph contains 0 node" 

 

Please see following command and response below':

emres-Air:model_optimizer emre$ python3.7 mo_tf.py --input_meta_graph /Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt-90728.meta  --output_dir /Users/emre/Documents/Temp/tensorflow_last/models/train/

Model Optimizer arguments:

Common parameters:

- Path to the Input Model: None

- Path for generated IR: /Users/emre/Documents/Temp/tensorflow_last/models/train/

- IR output name: model.ckpt-90728

- Log level: ERROR

- Batch: Not specified, inherited from the model

- Input layers: Not specified, inherited from the model

- Output layers: Not specified, inherited from the model

- Input shapes: Not specified, inherited from the model

- Mean values: Not specified

- Scale values: Not specified

- Scale factor: Not specified

- Precision of IR: FP32

- Enable fusing: True

- Enable grouped convolutions fusing: True

- Move mean values to preprocess section: None

- Reverse input channels: False

TensorFlow specific parameters:

- Input model in text protobuf format: False

- Path to model dump for TensorBoard: None

- List of shared libraries with TensorFlow custom layers implementation: None

- Update the configuration file with input/output node names: None

- Use configuration file used to generate the model with Object Detection API: None

- Use the config file: None

- Inference Engine found in: /opt/intel/openvino_2021.3.394/python/python3.7/openvino

Inference Engine version: 2.1.2021.3.0-2787-60059f2c755-releases/2021/3

Model Optimizer version:     2021.3.0-2787-60059f2c755-releases/2021/3

[ WARNING ]  

Detected not satisfied dependencies:

test-generator: not installed, required: == 0.1.1

 

Please install required versions of components or use install_prerequisites script

/opt/intel/openvino_2021.3.394/deployment_tools/model_optimizer/install_prerequisites/install_prerequisites_tf.sh

Note that install_prerequisites scripts may install additional components.

[ ANALYSIS INFO ]  It looks like there is IteratorGetNext as input

Run the Model Optimizer with:

--input "IteratorGetNext:0[],IteratorGetNext:1[-1],IteratorGetNext:2[-1 4],IteratorGetNext:3[-1],IteratorGetNext:4[-1],IteratorGetNext:5[-1],IteratorGetNext:6[-1],IteratorGetNext:7[-1],IteratorGetNext:8[-1],IteratorGetNext:9[-1],IteratorGetNext:10[-1],IteratorGetNext:11[-1],IteratorGetNext:12[-1 -1 3],IteratorGetNext:13[],IteratorGetNext:14[2],IteratorGetNext:15[]"

And replace all negative values with positive values

[ ERROR ]  Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.front.output_cut.OutputCut'>): Graph contains 0 node after executing <class 'extensions.front.output_cut.OutputCut'>. It considered as error because resulting IR will be empty which is not usual

 

Do you have any idea what I am doing wrong? Or do I have to use your command(with checkpoint parameter) with another value for checkpoint parameter?

 

PS:I have already tried your command with following checkpoint variables:model.ckpt-90728.index, model.ckpt-90728.meta, checkpoint and model.ckpt-90728.data-00000-of-00001 but none of them worked.

 

ex:

python3.7 mo_tf.py --input_model /Users/emre/Documents/Temp/tensorflow_last/models/train/graph.pbtxt --input_checkpoint /Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt-90728.data-00000-of-00001 --input_model_is_text --output_dir /Users/emre/Documents/Temp/tensorflow_last/models/train/

...

 

Thanks a lot in advance.

 

Emre Gun

Syamimi_Intel
Moderator
1,112 Views

Hi Emre Gun,

Can you share your model with us? So that we can try to replicate on our side.

 

 

Regards,

Syamimi


emregun
New Contributor I
1,104 Views

Hi Syamimi,

Sure. As I already mentioned, I just downloaded my model from Intel website:

 

python3.7 /opt/intel/openvino_2021.3.394/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name ssd_mobilenet_v1_fpn_coco

 

and trained it with following command:

python3.7 /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/legacy/train.py

--logtostderr
--train_dir=/Users/emre/Documents/Temp/tensorflow_last/models/train
--pipeline_config_path=/Users/emre/Documents/Temp/tensorflow_last/models/ssd_mobilenet_v1_fpn_shared_box_predictor_640x640_coco14_sync.config

 

This is my trained model:

https://www.dropbox.com/s/452qjknf1krmib6/train.zip?dl=0

 

Thank you very much.

Note:my config file is attached.

 

Best regards

Emre

emregun
New Contributor I
1,020 Views

Hi Syamimi


I would be grateful if you could share any other ideas-

I prepared shortest repro steps. I guess you can also reproduce it:

Requirements:

Python:3.7
MacOS:Big Sur 11.2.1
Openvino:openvino_2021.3.394
Tensorflow:1.15.0

Repro Steps:

1-

1.1Command:python3.7 /opt/intel/openvino_2021.3.394/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name ssd_mobilenet_v1_fpn_coco

1.1Response:

################|| Downloading ssd_mobilenet_v1_fpn_coco ||################

 

========== Downloading /opt/intel/openvino_2021.3.394/deployment_tools/open_model_zoo/tools/downloader/public/ssd_mobilenet_v1_fpn_coco/ssd_mobilenet_v1_fpn_shared_box_predictor_640x640_coco14_sync_2018_07_03.tar.gz

... 100%, 132484 KB, 4103 KB/s, 32 seconds passed

 

========== Unpacking /opt/intel/openvino_2021.3.394/deployment_tools/open_model_zoo/tools/downloader/public/ssd_mobilenet_v1_fpn_coco/ssd_mobilenet_v1_fpn_shared_box_predictor_640x640_coco14_sync_2018_07_03.tar.gz

2-

2.1Command:

python3.7 /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/legacy/train.py

--logtostderr
--train_dir=/Users/emre/Documents/Temp/tensorflow_last/models/train
--pipeline_config_path=/Users/emre/Documents/Temp/tensorflow_last/models/ssd_mobilenet_v1_fpn_shared_box_predictor_640x640_coco14_sync.config

Note: ssd_mobilenet_v1_fpn_shared_box_predictor_640x640_coco14_sync.config attached as ssd_mobilenet_v1_fpn_shared_box_predictor_640x640_coco14_sync.txt

2.2Response:

WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/absl/app.py:251: main (from __main__) is deprecated and will be removed in a future version.
Instructions for updating:
Use object_detection/model_main.py.
W0718 18:54:17.160089 4516814336 deprecation.py:323] From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/absl/app.py:251: main (from __main__) is deprecated and will be removed in a future version.
Instructions for updating:
Use object_detection/model_main.py.
WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/legacy/trainer.py:265: create_global_step (from tf_slim.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.create_global_step
W0718 18:54:17.177958 4516814336 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/legacy/trainer.py:265: create_global_step (from tf_slim.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.create_global_step
INFO:tensorflow:Reading unweighted datasets: ['/Users/emre/Documents/Temp/tensorflow_last/models/tf_record/train.record']
I0718 18:54:17.207098 4516814336 dataset_builder.py:163] Reading unweighted datasets: ['/Users/emre/Documents/Temp/tensorflow_last/models/tf_record/train.record']
INFO:tensorflow:Reading record datasets for input file: ['/Users/emre/Documents/Temp/tensorflow_last/models/tf_record/train.record']
I0718 18:54:17.208154 4516814336 dataset_builder.py:80] Reading record datasets for input file: ['/Users/emre/Documents/Temp/tensorflow_last/models/tf_record/train.record']
INFO:tensorflow:Number of filenames to read: 1
I0718 18:54:17.208302 4516814336 dataset_builder.py:81] Number of filenames to read: 1
WARNING:tensorflow:num_readers has been reduced to 1 to match input file shards.
W0718 18:54:17.208404 4516814336 dataset_builder.py:88] num_readers has been reduced to 1 to match input file shards.
WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/builders/dataset_builder.py:105: parallel_interleave (from tensorflow.python.data.experimental.ops.interleave_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.data.Dataset.interleave(map_func, cycle_length, block_length, num_parallel_calls=tf.data.experimental.AUTOTUNE)` instead. If sloppy execution is desired, use `tf.data.Options.experimental_determinstic`.
W0718 18:54:17.216276 4516814336 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/builders/dataset_builder.py:105: parallel_interleave (from tensorflow.python.data.experimental.ops.interleave_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.data.Dataset.interleave(map_func, cycle_length, block_length, num_parallel_calls=tf.data.experimental.AUTOTUNE)` instead. If sloppy execution is desired, use `tf.data.Options.experimental_determinstic`.
WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/builders/dataset_builder.py:237: DatasetV1.map_with_legacy_function (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.data.Dataset.map()
W0718 18:54:17.245516 4516814336 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/builders/dataset_builder.py:237: DatasetV1.map_with_legacy_function (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.data.Dataset.map()
WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/builders/dataset_builder.py:49: DatasetV1.make_initializable_iterator (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `for ... in dataset:` to iterate over a dataset. If using `tf.estimator`, return the `Dataset` object directly from your input function. As a last resort, you can use `tf.compat.v1.data.make_initializable_iterator(dataset)`.
W0718 18:54:20.219524 4516814336 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/builders/dataset_builder.py:49: DatasetV1.make_initializable_iterator (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `for ... in dataset:` to iterate over a dataset. If using `tf.estimator`, return the `Dataset` object directly from your input function. As a last resort, you can use `tf.compat.v1.data.make_initializable_iterator(dataset)`.
WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/core/preprocessor.py:199: sample_distorted_bounding_box (from tensorflow.python.ops.image_ops_impl) is deprecated and will be removed in a future version.
Instructions for updating:
`seed2` arg is deprecated.Use sample_distorted_bounding_box_v2 instead.
W0718 18:54:20.254029 4516814336 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/core/preprocessor.py:199: sample_distorted_bounding_box (from tensorflow.python.ops.image_ops_impl) is deprecated and will be removed in a future version.
Instructions for updating:
`seed2` arg is deprecated.Use sample_distorted_bounding_box_v2 instead.
WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/core/box_list_ops.py:234: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
W0718 18:54:20.271087 4516814336 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/core/box_list_ops.py:234: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/core/batcher.py:101: batch (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.batch(batch_size)` (or `padded_batch(...)` if `dynamic_pad=True`).
W0718 18:54:20.323724 4516814336 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/core/batcher.py:101: batch (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.batch(batch_size)` (or `padded_batch(...)` if `dynamic_pad=True`).
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/training/input.py:752: QueueRunner.__init__ (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
W0718 18:54:20.327262 4516814336 deprecation.py:323] From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/training/input.py:752: QueueRunner.__init__ (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/training/input.py:752: add_queue_runner (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
W0718 18:54:20.328144 4516814336 deprecation.py:323] From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/training/input.py:752: add_queue_runner (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tf_slim/layers/layers.py:1089: Layer.apply (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.
Instructions for updating:
Please use `layer.__call__` method instead.
W0718 18:54:20.444861 4516814336 deprecation.py:323] From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tf_slim/layers/layers.py:1089: Layer.apply (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.
Instructions for updating:
Please use `layer.__call__` method instead.
W0718 18:54:26.363759 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_0/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.363924 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_0/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.363995 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_0/weights/Momentum] is not available in checkpoint
W0718 18:54:26.364053 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_10_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.364105 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_10_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.364164 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_10_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.364215 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_10_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.364264 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_10_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.364326 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_10_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.364376 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_11_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.364424 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_11_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.364480 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_11_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.364529 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_11_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.364583 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_11_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.364640 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_11_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.364689 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_12_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.364739 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_12_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.364794 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_12_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.364844 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_12_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.364892 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_12_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.364949 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_12_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.364998 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_13_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.365048 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_13_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.365104 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_13_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.365154 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_13_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.365201 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_13_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.365260 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_13_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.365309 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_1_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.365357 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_1_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.365413 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_1_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.365461 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_1_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.365509 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_1_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.365564 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_1_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.365614 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_2_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.365663 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_2_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.365718 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_2_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.365765 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_2_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.365814 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_2_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.365869 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_2_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.365917 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_3_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.365966 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_3_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.366021 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_3_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.366070 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_3_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.366117 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_3_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.366173 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_3_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.366220 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_4_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.366268 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_4_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.366323 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_4_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.366373 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_4_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.366421 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_4_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.366477 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_4_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.366528 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_5_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.366576 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_5_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.366632 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_5_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.366681 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_5_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.366729 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_5_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.366786 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_5_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.366833 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_6_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.366883 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_6_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.366938 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_6_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.366986 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_6_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.367034 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_6_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.367089 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_6_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.367139 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_7_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.367187 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_7_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.367243 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_7_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.367290 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_7_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.367340 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_7_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.367396 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_7_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.367444 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_8_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.367493 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_8_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.367548 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_8_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.367598 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_8_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.367645 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_8_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.367702 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_8_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.367750 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_9_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.367799 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_9_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.367855 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_9_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.367903 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_9_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.367951 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_9_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.368007 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_9_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.368057 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_14/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.368117 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_14/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.368188 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_14/weights/Momentum] is not available in checkpoint
W0718 18:54:26.368242 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_15/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.368291 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_15/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.368346 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_15/weights/Momentum] is not available in checkpoint
W0718 18:54:26.368396 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/projection_1/biases/Momentum] is not available in checkpoint
W0718 18:54:26.368445 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/projection_1/weights/Momentum] is not available in checkpoint
W0718 18:54:26.368494 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/projection_2/biases/Momentum] is not available in checkpoint
W0718 18:54:26.368544 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/projection_2/weights/Momentum] is not available in checkpoint
W0718 18:54:26.368592 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/projection_3/biases/Momentum] is not available in checkpoint
W0718 18:54:26.368642 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/projection_3/weights/Momentum] is not available in checkpoint
W0718 18:54:26.368690 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/smoothing_1/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.368739 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/smoothing_1/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.368794 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/smoothing_1/weights/Momentum] is not available in checkpoint
W0718 18:54:26.368843 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/smoothing_2/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.368890 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/smoothing_2/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.368944 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/smoothing_2/weights/Momentum] is not available in checkpoint
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tf_slim/learning.py:734: Supervisor.__init__ (from tensorflow.python.training.supervisor) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.MonitoredTrainingSession
W0718 18:54:26.870261 4516814336 deprecation.py:323] From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tf_slim/learning.py:734: Supervisor.__init__ (from tensorflow.python.training.supervisor) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.MonitoredTrainingSession
2021-07-18 18:54:27.558277: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2021-07-18 18:54:27.576813: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fcf017915e0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2021-07-18 18:54:27.576830: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
INFO:tensorflow:Restoring parameters from /Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt-0
I0718 18:54:27.579802 4516814336 saver.py:1284] Restoring parameters from /Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt-0
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/training/saver.py:1069: get_checkpoint_mtimes (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file utilities to get mtimes.
W0718 18:54:28.788303 4516814336 deprecation.py:323] From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/training/saver.py:1069: get_checkpoint_mtimes (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file utilities to get mtimes.
INFO:tensorflow:Running local_init_op.
I0718 18:54:28.789540 4516814336 session_manager.py:500] Running local_init_op.
INFO:tensorflow:Done running local_init_op.
I0718 18:54:29.388906 4516814336 session_manager.py:502] Done running local_init_op.
INFO:tensorflow:Starting Session.
I0718 18:54:33.949297 4516814336 learning.py:746] Starting Session.
INFO:tensorflow:Saving checkpoint to path /Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt
I0718 18:54:34.238749 123145356120064 supervisor.py:1117] Saving checkpoint to path /Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt
INFO:tensorflow:Starting Queues.
I0718 18:54:34.241323 4516814336 learning.py:760] Starting Queues.
INFO:tensorflow:global_step/sec: 0
I0718 18:54:39.705050 123145350864896 supervisor.py:1099] global_step/sec: 0
INFO:tensorflow:Recording summary at step 0.
I0718 18:54:44.180414 123145345609728 supervisor.py:1050] Recording summary at step 0.
INFO:tensorflow:global step 1: loss = 2.3208 (22.770 sec/step)
I0718 18:54:57.341979 4516814336 learning.py:512] global step 1: loss = 2.3208 (22.770 sec/step)
INFO:tensorflow:global step 2: loss = 2.0617 (9.843 sec/step)
I0718 18:55:07.430543 4516814336 learning.py:512] global step 2: loss = 2.0617 (9.843 sec/step)

3-

3.1Command:

python3.7 mo_tf.py --input_meta_graph /Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt-0.meta  --output_dir /Users/emre/Documents/Temp/tensorflow_last/models/train/

3.2Response:

Model Optimizer arguments:

Common parameters:

- Path to the Input Model: None

- Path for generated IR: /Users/emre/Documents/Temp/tensorflow_last/models/train/

- IR output name: model.ckpt-0

- Log level: ERROR

- Batch: Not specified, inherited from the model

- Input layers: Not specified, inherited from the model

- Output layers: Not specified, inherited from the model

- Input shapes: Not specified, inherited from the model

- Mean values: Not specified

- Scale values: Not specified

- Scale factor: Not specified

- Precision of IR: FP32

- Enable fusing: True

- Enable grouped convolutions fusing: True

- Move mean values to preprocess section: None

- Reverse input channels: False

TensorFlow specific parameters:

- Input model in text protobuf format: False

- Path to model dump for TensorBoard: None

- List of shared libraries with TensorFlow custom layers implementation: None

- Update the configuration file with input/output node names: None

- Use configuration file used to generate the model with Object Detection API: None

- Use the config file: None

- Inference Engine found in: /opt/intel/openvino_2021.3.394/python/python3.7/openvino

Inference Engine version: 2.1.2021.3.0-2787-60059f2c755-releases/2021/3

Model Optimizer version:     2021.3.0-2787-60059f2c755-releases/2021/3

[ WARNING ]  

Detected not satisfied dependencies:

test-generator: not installed, required: == 0.1.1

 

Please install required versions of components or use install_prerequisites script

/opt/intel/openvino_2021.3.394/deployment_tools/model_optimizer/install_prerequisites/install_prerequisites_tf.sh

Note that install_prerequisites scripts may install additional components.

[ ANALYSIS INFO ]  It looks like there is IteratorGetNext as input

Run the Model Optimizer with:

--input "IteratorGetNext:0[],IteratorGetNext:1[-1],IteratorGetNext:2[-1 4],IteratorGetNext:3[-1],IteratorGetNext:4[-1],IteratorGetNext:5[-1],IteratorGetNext:6[-1],IteratorGetNext:7[-1],IteratorGetNext:8[-1],IteratorGetNext:9[-1],IteratorGetNext:10[-1],IteratorGetNext:11[-1],IteratorGetNext:12[-1 -1 3],IteratorGetNext:13[],IteratorGetNext:14[2],IteratorGetNext:15[]"

And replace all negative values with positive values

[ ERROR ]  Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.front.output_cut.OutputCut'>): Graph contains 0 node after executing <class 'extensions.front.output_cut.OutputCut'>. It considered as error because resulting IR will be empty which is not usual

 

Thank you very much in advance

Emre

emregun
New Contributor I
1,020 Views

Hi Syamimi,
 
I would be grateful, if you could share any other ideas.
I described the shortest repro steps below. I guess you can also reproduce easily.
 

Requirements:

Python:3.7
MacOS:Big Sur 11.2.1
Openvino:openvino_2021.3.394
Tensorflow:1.15.0

 

Repro Steps:

1.1Command

sudo python3.7 /opt/intel/openvino_2021.3.394/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name ssd_mobilenet_v1_fpn_coco

1.2Response

Password:

################|| Downloading ssd_mobilenet_v1_fpn_coco ||################

 

========== Downloading /opt/intel/openvino_2021.3.394/deployment_tools/open_model_zoo/tools/downloader/public/ssd_mobilenet_v1_fpn_coco/ssd_mobilenet_v1_fpn_shared_box_predictor_640x640_coco14_sync_2018_07_03.tar.gz

... 100%, 132484 KB, 4103 KB/s, 32 seconds passed

 

========== Unpacking /opt/intel/openvino_2021.3.394/deployment_tools/open_model_zoo/tools/downloader/public/ssd_mobilenet_v1_fpn_coco/ssd_mobilenet_v1_fpn_shared_box_predictor_640x640_coco14_sync_2018_07_03.tar.gz

2.1Command

python3.7 /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/legacy/train.py

--logtostderr
--train_dir=/Users/emre/Documents/Temp/tensorflow_last/models/train
--pipeline_config_path=/Users/emre/Documents/Temp/tensorflow_last/models/ssd_mobilenet_v1_fpn_shared_box_predictor_640x640_coco14_sync.config

Note:Config file attached as txt file. (ssd_mobilenet_v1_fpn_shared_box_predictor_640x640_coco14_sync.txt)

2.2Response

WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/absl/app.py:251: main (from __main__) is deprecated and will be removed in a future version.
Instructions for updating:
Use object_detection/model_main.py.
W0718 18:54:17.160089 4516814336 deprecation.py:323] From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/absl/app.py:251: main (from __main__) is deprecated and will be removed in a future version.
Instructions for updating:
Use object_detection/model_main.py.
WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/legacy/trainer.py:265: create_global_step (from tf_slim.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.create_global_step
W0718 18:54:17.177958 4516814336 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/legacy/trainer.py:265: create_global_step (from tf_slim.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.create_global_step
INFO:tensorflow:Reading unweighted datasets: ['/Users/emre/Documents/Temp/tensorflow_last/models/tf_record/train.record']
I0718 18:54:17.207098 4516814336 dataset_builder.py:163] Reading unweighted datasets: ['/Users/emre/Documents/Temp/tensorflow_last/models/tf_record/train.record']
INFO:tensorflow:Reading record datasets for input file: ['/Users/emre/Documents/Temp/tensorflow_last/models/tf_record/train.record']
I0718 18:54:17.208154 4516814336 dataset_builder.py:80] Reading record datasets for input file: ['/Users/emre/Documents/Temp/tensorflow_last/models/tf_record/train.record']
INFO:tensorflow:Number of filenames to read: 1
I0718 18:54:17.208302 4516814336 dataset_builder.py:81] Number of filenames to read: 1
WARNING:tensorflow:num_readers has been reduced to 1 to match input file shards.
W0718 18:54:17.208404 4516814336 dataset_builder.py:88] num_readers has been reduced to 1 to match input file shards.
WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/builders/dataset_builder.py:105: parallel_interleave (from tensorflow.python.data.experimental.ops.interleave_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.data.Dataset.interleave(map_func, cycle_length, block_length, num_parallel_calls=tf.data.experimental.AUTOTUNE)` instead. If sloppy execution is desired, use `tf.data.Options.experimental_determinstic`.
W0718 18:54:17.216276 4516814336 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/builders/dataset_builder.py:105: parallel_interleave (from tensorflow.python.data.experimental.ops.interleave_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.data.Dataset.interleave(map_func, cycle_length, block_length, num_parallel_calls=tf.data.experimental.AUTOTUNE)` instead. If sloppy execution is desired, use `tf.data.Options.experimental_determinstic`.
WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/builders/dataset_builder.py:237: DatasetV1.map_with_legacy_function (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.data.Dataset.map()
W0718 18:54:17.245516 4516814336 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/builders/dataset_builder.py:237: DatasetV1.map_with_legacy_function (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.data.Dataset.map()
WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/builders/dataset_builder.py:49: DatasetV1.make_initializable_iterator (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `for ... in dataset:` to iterate over a dataset. If using `tf.estimator`, return the `Dataset` object directly from your input function. As a last resort, you can use `tf.compat.v1.data.make_initializable_iterator(dataset)`.
W0718 18:54:20.219524 4516814336 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/builders/dataset_builder.py:49: DatasetV1.make_initializable_iterator (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `for ... in dataset:` to iterate over a dataset. If using `tf.estimator`, return the `Dataset` object directly from your input function. As a last resort, you can use `tf.compat.v1.data.make_initializable_iterator(dataset)`.
WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/core/preprocessor.py:199: sample_distorted_bounding_box (from tensorflow.python.ops.image_ops_impl) is deprecated and will be removed in a future version.
Instructions for updating:
`seed2` arg is deprecated.Use sample_distorted_bounding_box_v2 instead.
W0718 18:54:20.254029 4516814336 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/core/preprocessor.py:199: sample_distorted_bounding_box (from tensorflow.python.ops.image_ops_impl) is deprecated and will be removed in a future version.
Instructions for updating:
`seed2` arg is deprecated.Use sample_distorted_bounding_box_v2 instead.
WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/core/box_list_ops.py:234: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
W0718 18:54:20.271087 4516814336 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/core/box_list_ops.py:234: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/core/batcher.py:101: batch (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.batch(batch_size)` (or `padded_batch(...)` if `dynamic_pad=True`).
W0718 18:54:20.323724 4516814336 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/core/batcher.py:101: batch (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.batch(batch_size)` (or `padded_batch(...)` if `dynamic_pad=True`).
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/training/input.py:752: QueueRunner.__init__ (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
W0718 18:54:20.327262 4516814336 deprecation.py:323] From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/training/input.py:752: QueueRunner.__init__ (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/training/input.py:752: add_queue_runner (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
W0718 18:54:20.328144 4516814336 deprecation.py:323] From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/training/input.py:752: add_queue_runner (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tf_slim/layers/layers.py:1089: Layer.apply (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.
Instructions for updating:
Please use `layer.__call__` method instead.
W0718 18:54:20.444861 4516814336 deprecation.py:323] From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tf_slim/layers/layers.py:1089: Layer.apply (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.
Instructions for updating:
Please use `layer.__call__` method instead.
W0718 18:54:26.363759 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_0/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.363924 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_0/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.363995 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_0/weights/Momentum] is not available in checkpoint
W0718 18:54:26.364053 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_10_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.364105 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_10_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.364164 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_10_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.364215 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_10_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.364264 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_10_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.364326 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_10_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.364376 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_11_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.364424 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_11_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.364480 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_11_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.364529 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_11_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.364583 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_11_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.364640 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_11_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.364689 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_12_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.364739 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_12_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.364794 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_12_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.364844 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_12_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.364892 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_12_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.364949 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_12_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.364998 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_13_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.365048 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_13_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.365104 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_13_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.365154 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_13_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.365201 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_13_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.365260 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_13_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.365309 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_1_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.365357 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_1_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.365413 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_1_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.365461 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_1_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.365509 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_1_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.365564 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_1_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.365614 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_2_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.365663 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_2_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.365718 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_2_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.365765 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_2_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.365814 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_2_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.365869 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_2_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.365917 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_3_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.365966 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_3_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.366021 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_3_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.366070 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_3_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.366117 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_3_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.366173 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_3_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.366220 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_4_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.366268 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_4_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.366323 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_4_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.366373 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_4_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.366421 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_4_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.366477 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_4_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.366528 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_5_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.366576 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_5_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.366632 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_5_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.366681 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_5_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.366729 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_5_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.366786 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_5_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.366833 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_6_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.366883 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_6_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.366938 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_6_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.366986 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_6_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.367034 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_6_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.367089 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_6_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.367139 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_7_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.367187 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_7_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.367243 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_7_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.367290 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_7_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.367340 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_7_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.367396 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_7_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.367444 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_8_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.367493 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_8_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.367548 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_8_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.367598 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_8_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.367645 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_8_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.367702 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_8_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.367750 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_9_depthwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.367799 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_9_depthwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.367855 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_9_depthwise/depthwise_weights/Momentum] is not available in checkpoint
W0718 18:54:26.367903 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_9_pointwise/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.367951 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_9_pointwise/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.368007 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/Conv2d_9_pointwise/weights/Momentum] is not available in checkpoint
W0718 18:54:26.368057 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_14/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.368117 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_14/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.368188 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_14/weights/Momentum] is not available in checkpoint
W0718 18:54:26.368242 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_15/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.368291 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_15/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.368346 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_15/weights/Momentum] is not available in checkpoint
W0718 18:54:26.368396 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/projection_1/biases/Momentum] is not available in checkpoint
W0718 18:54:26.368445 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/projection_1/weights/Momentum] is not available in checkpoint
W0718 18:54:26.368494 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/projection_2/biases/Momentum] is not available in checkpoint
W0718 18:54:26.368544 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/projection_2/weights/Momentum] is not available in checkpoint
W0718 18:54:26.368592 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/projection_3/biases/Momentum] is not available in checkpoint
W0718 18:54:26.368642 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/projection_3/weights/Momentum] is not available in checkpoint
W0718 18:54:26.368690 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/smoothing_1/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.368739 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/smoothing_1/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.368794 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/smoothing_1/weights/Momentum] is not available in checkpoint
W0718 18:54:26.368843 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/smoothing_2/BatchNorm/beta/Momentum] is not available in checkpoint
W0718 18:54:26.368890 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/smoothing_2/BatchNorm/gamma/Momentum] is not available in checkpoint
W0718 18:54:26.368944 4516814336 variables_helper.py:156] Variable [FeatureExtractor/MobilenetV1/fpn/smoothing_2/weights/Momentum] is not available in checkpoint
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tf_slim/learning.py:734: Supervisor.__init__ (from tensorflow.python.training.supervisor) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.MonitoredTrainingSession
W0718 18:54:26.870261 4516814336 deprecation.py:323] From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tf_slim/learning.py:734: Supervisor.__init__ (from tensorflow.python.training.supervisor) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.MonitoredTrainingSession
2021-07-18 18:54:27.558277: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2021-07-18 18:54:27.576813: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fcf017915e0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2021-07-18 18:54:27.576830: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
INFO:tensorflow:Restoring parameters from /Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt-0
I0718 18:54:27.579802 4516814336 saver.py:1284] Restoring parameters from /Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt-0
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/training/saver.py:1069: get_checkpoint_mtimes (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file utilities to get mtimes.
W0718 18:54:28.788303 4516814336 deprecation.py:323] From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/training/saver.py:1069: get_checkpoint_mtimes (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file utilities to get mtimes.
INFO:tensorflow:Running local_init_op.
I0718 18:54:28.789540 4516814336 session_manager.py:500] Running local_init_op.
INFO:tensorflow:Done running local_init_op.
I0718 18:54:29.388906 4516814336 session_manager.py:502] Done running local_init_op.
INFO:tensorflow:Starting Session.
I0718 18:54:33.949297 4516814336 learning.py:746] Starting Session.
INFO:tensorflow:Saving checkpoint to path /Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt
I0718 18:54:34.238749 123145356120064 supervisor.py:1117] Saving checkpoint to path /Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt
INFO:tensorflow:Starting Queues.
I0718 18:54:34.241323 4516814336 learning.py:760] Starting Queues.
INFO:tensorflow:global_step/sec: 0
I0718 18:54:39.705050 123145350864896 supervisor.py:1099] global_step/sec: 0
INFO:tensorflow:Recording summary at step 0.
I0718 18:54:44.180414 123145345609728 supervisor.py:1050] Recording summary at step 0.
INFO:tensorflow:global step 1: loss = 2.3208 (22.770 sec/step)
I0718 18:54:57.341979 4516814336 learning.py:512] global step 1: loss = 2.3208 (22.770 sec/step)
INFO:tensorflow:global step 2: loss = 2.0617 (9.843 sec/step)
I0718 18:55:07.430543 4516814336 learning.py:512] global step 2: loss = 2.0617 (9.843 sec/step)

Note: you can just stop the training after second step.      

3.1Command

python3.7 mo_tf.py --input_meta_graph /Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt-0.meta  --output_dir /Users/emre/Documents/Temp/tensorflow_last/models/train/

3.2Response

Model Optimizer arguments:

Common parameters:

- Path to the Input Model: None

- Path for generated IR: /Users/emre/Documents/Temp/tensorflow_last/models/train/

- IR output name: model.ckpt-0

- Log level: ERROR

- Batch: Not specified, inherited from the model

- Input layers: Not specified, inherited from the model

- Output layers: Not specified, inherited from the model

- Input shapes: Not specified, inherited from the model

- Mean values: Not specified

- Scale values: Not specified

- Scale factor: Not specified

- Precision of IR: FP32

- Enable fusing: True

- Enable grouped convolutions fusing: True

- Move mean values to preprocess section: None

- Reverse input channels: False

TensorFlow specific parameters:

- Input model in text protobuf format: False

- Path to model dump for TensorBoard: None

- List of shared libraries with TensorFlow custom layers implementation: None

- Update the configuration file with input/output node names: None

- Use configuration file used to generate the model with Object Detection API: None

- Use the config file: None

- Inference Engine found in: /opt/intel/openvino_2021.3.394/python/python3.7/openvino

Inference Engine version: 2.1.2021.3.0-2787-60059f2c755-releases/2021/3

Model Optimizer version:     2021.3.0-2787-60059f2c755-releases/2021/3

[ WARNING ]  

Detected not satisfied dependencies:

test-generator: not installed, required: == 0.1.1

 

Please install required versions of components or use install_prerequisites script

/opt/intel/openvino_2021.3.394/deployment_tools/model_optimizer/install_prerequisites/install_prerequisites_tf.sh

Note that install_prerequisites scripts may install additional components.

[ ANALYSIS INFO ]  It looks like there is IteratorGetNext as input

Run the Model Optimizer with:

--input "IteratorGetNext:0[],IteratorGetNext:1[-1],IteratorGetNext:2[-1 4],IteratorGetNext:3[-1],IteratorGetNext:4[-1],IteratorGetNext:5[-1],IteratorGetNext:6[-1],IteratorGetNext:7[-1],IteratorGetNext:8[-1],IteratorGetNext:9[-1],IteratorGetNext:10[-1],IteratorGetNext:11[-1],IteratorGetNext:12[-1 -1 3],IteratorGetNext:13[],IteratorGetNext:14[2],IteratorGetNext:15[]"

And replace all negative values with positive values

[ ERROR ]  Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.front.output_cut.OutputCut'>): Graph contains 0 node after executing <class 'extensions.front.output_cut.OutputCut'>. It considered as error because resulting IR will be empty which is not usual

 

Thank you very much in advance.

 

Emre

 

emregun
New Contributor I
1,055 Views

Hi Syamimi,

 

I would be grateful, if you could share any other ideas. I described the shortest repro steps below in attachment. (Somehow I cannot post it directly.) I guess you can also reproduce easily.

 

Thank you very much in advance.

 

Emre

Syamimi_Intel
Moderator
1,000 Views

Hi Emre Gun,

We tried to convert your custom model with MO command, which works for OMZ version of ssd_mobilenet_v1_fpn_coco and got the same error that none of the following nodes is in the graph: detection_scores, detection_boxes, num_detections (output nodes), image_tensor (an input node).

 

MO command that we used:

sudo /usr/bin/python3 -- /opt/intel/openvino_2021.4.582/deployment_tools/model_optimizer/mo.py --framework=tf --data_type=FP16 --output_dir=/opt/intel/openvino_2021.4.582/deployment_tools/open_model_zoo/tools/downloader/public/ssd_mobilenet_v1_fpn_coco/FP16 --model_name=ssd_mobilenet_v1_fpn_coco --reverse_input_channels '--input_shape=[1,640,640,3]' --input=image_tensor --output=detection_scores,detection_boxes,num_detections --transformations_config=/opt/intel/openvino_2021.4.582/deployment_tools/model_optimizer/extensions/front/tf/ssd_support_api_v1.14.json --tensorflow_object_detection_api_pipeline_config=/opt/intel/openvino_2021.4.582/deployment_tools/open_model_zoo/tools/downloader/public/ssd_mobilenet_v1_fpn_coco/ssd_mobilenet_v1_fpn_shared_box_predictor_640x640_coco14_sync_2018_07_03/pipeline.config --input_meta_graph=/home/user/train/train/model.ckpt-90728.meta

 

 

If no nodes are specified, we got the same error as you:

[ ERROR ] Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.front.output_cut.OutputCut'>): Graph contains 0 node after executing <class 'extensions.front.output_cut.OutputCut'>. It considered as error because resulting IR will be empty which is not usual

 

It is obvious that your model’s structure is different from our ssd_mobilenet_v1_fpn_coco model in the OMZ.

 

Usually, for such cases it was possible to check input and output nodes within a model through Netron model viewer - https://github.com/lutzroeder/netron

And we can say it is still possible for OMZ version of ssd_mobilenet_v1_fpn_coco model. All nodes are visible in the graph for it. Unfortunately, Netron can’t open any of the meta graph models that you shared with us. We believe this is necessary to get this information for further conversion via the Model Optimizer.

 

You may try to convert the custom model into a different format (e.g. TensorFlow 2 or standard TF1 *.pb format), so it should be accessible through Netron software to check input and output nodes.

 

 

Regards,

Syamimi


emregun
New Contributor I
980 Views

Hi Syamimi,

 

Thanks for the reply. I would be grateful if you could support me for the following 2 questions:

 

1-

"It is obvious that your model’s structure is different from our ssd_mobilenet_v1_fpn_coco model in the OMZ."

Could you please tell me what OMZ version of ssd_mobilenet_v1_fpn_coc means? (I am new in openvino)

I just downloaded my model with openvino downloader as I already mentioned above with following command:

 

python3.7 /opt/intel/openvino_2021.3.394/deployment_tools/open_model_zoo/tools/downloader/downloader.py--name ssd_mobilenet_v1_fpn_coco

 

Do you mean that I should not use it, and there is another OMZ version? If there is another OMZ version,

Where can I load it?

 

2-Last night, I achieved to create my .pb file with following command(Sorry I could not have time to write you):

 

Command:

/Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/export_inference_graph.py

 

--input_type=image_tensor

--pipeline_config_path=/Users/emre/Documents/Temp/tensorflow_last/models/ssd_mobilenet_v1_fpn_shared_box_predictor_640x640_coco14_sync.config

--trained_checkpoint_prefix=/Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt-102537

--output_directory=/Users/emre/Documents/Temp/tensorflow_last/models/train

 

 

 

Response:

/usr/local/bin/python3.7 /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/export_inference_graph.py --input_type=image_tensor --pipeline_config_path=/Users/emre/Documents/Temp/tensorflow_last/models/ssd_mobilenet_v1_fpn_shared_box_predictor_640x640_coco14_sync.config --trained_checkpoint_prefix=/Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt-102537 --output_directory=/Users/emre/Documents/Temp/tensorflow_last/models/train

['/Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection', '/Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection', '/Library/Frameworks/Python.framework/Versions/3.7/lib/python37.zip', '/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7', '/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/lib-dynload', '/Users/emre/Library/Python/3.7/lib/python/site-packages', '/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages', '/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/aeosa', '/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/kivy_ios-1.3.0.dev0-py3.7.egg']

WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tf_slim/layers/layers.py:1089: Layer.apply (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.

Instructions for updating:

Please use `layer.__call__` method instead.

W0723 14:18:02.881181 4487224832 deprecation.py:323] From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tf_slim/layers/layers.py:1089: Layer.apply (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.

Instructions for updating:

Please use `layer.__call__` method instead.

WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/core/post_processing.py:601: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.

Instructions for updating:

Use tf.where in 2.0, which has the same broadcast rule as np.where

W0723 14:18:05.762117 4487224832 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/core/post_processing.py:601: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.

Instructions for updating:

Use tf.where in 2.0, which has the same broadcast rule as np.where

WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/exporter.py:474: get_or_create_global_step (from tf_slim.ops.variables) is deprecated and will be removed in a future version.

Instructions for updating:

Please switch to tf.train.get_or_create_global_step

W0723 14:18:06.261592 4487224832 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/exporter.py:474: get_or_create_global_step (from tf_slim.ops.variables) is deprecated and will be removed in a future version.

Instructions for updating:

Please switch to tf.train.get_or_create_global_step

WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/exporter.py:653: print_model_analysis (from tensorflow.contrib.tfprof.model_analyzer) is deprecated and will be removed after 2018-01-01.

Instructions for updating:

Use `tf.profiler.profile(graph, run_meta, op_log, cmd, options)`. Build `options` with `tf.profiler.ProfileOptionBuilder`. See README.md for details

W0723 14:18:06.266640 4487224832 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/exporter.py:653: print_model_analysis (from tensorflow.contrib.tfprof.model_analyzer) is deprecated and will be removed after 2018-01-01.

Instructions for updating:

Use `tf.profiler.profile(graph, run_meta, op_log, cmd, options)`. Build `options` with `tf.profiler.ProfileOptionBuilder`. See README.md for details

WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/profiler/internal/flops_registry.py:142: tensor_shape_from_node_def_name (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version.

Instructions for updating:

Use `tf.compat.v1.graph_util.tensor_shape_from_node_def_name`

W0723 14:18:06.267143 4487224832 deprecation.py:323] From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/profiler/internal/flops_registry.py:142: tensor_shape_from_node_def_name (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version.

Instructions for updating:

Use `tf.compat.v1.graph_util.tensor_shape_from_node_def_name`

156 ops no flops stats due to incomplete shapes.

Parsing Inputs...

Incomplete shape.

 

=========================Options=============================

-max_depth 10000

-min_bytes 0

-min_peak_bytes 0

-min_residual_bytes 0

-min_output_bytes 0

-min_micros 0

-min_accelerator_micros 0

-min_cpu_micros 0

-min_params 0

-min_float_ops 0

-min_occurrence 0

-step -1

-order_by name

-account_type_regexes _trainable_variables

-start_name_regexes .*

-trim_name_regexes .*BatchNorm.*

-show_name_regexes .*

-hide_name_regexes

-account_displayed_op_only true

-select params

-output stdout:

 

==================Model Analysis Report======================

Incomplete shape.

 

Doc:

scope: The nodes in the model graph are organized by their names, which is hierarchical like filesystem.

param: Number of parameters (in the Variable).

 

Profile:

node name | # parameters

_TFProfRoot (--/10.87m params)

FeatureExtractor (--/6.00m params)

FeatureExtractor/MobilenetV1 (--/6.00m params)

FeatureExtractor/MobilenetV1/Conv2d_0 (--/864 params)

FeatureExtractor/MobilenetV1/Conv2d_0/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_0/weights (3x3x3x32, 864/864 params)

FeatureExtractor/MobilenetV1/Conv2d_10_depthwise (--/4.61k params)

FeatureExtractor/MobilenetV1/Conv2d_10_depthwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_10_depthwise/depthwise_weights (3x3x512x1, 4.61k/4.61k params)

FeatureExtractor/MobilenetV1/Conv2d_10_pointwise (--/262.14k params)

FeatureExtractor/MobilenetV1/Conv2d_10_pointwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_10_pointwise/weights (1x1x512x512, 262.14k/262.14k params)

FeatureExtractor/MobilenetV1/Conv2d_11_depthwise (--/4.61k params)

FeatureExtractor/MobilenetV1/Conv2d_11_depthwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_11_depthwise/depthwise_weights (3x3x512x1, 4.61k/4.61k params)

FeatureExtractor/MobilenetV1/Conv2d_11_pointwise (--/262.14k params)

FeatureExtractor/MobilenetV1/Conv2d_11_pointwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_11_pointwise/weights (1x1x512x512, 262.14k/262.14k params)

FeatureExtractor/MobilenetV1/Conv2d_12_depthwise (--/4.61k params)

FeatureExtractor/MobilenetV1/Conv2d_12_depthwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_12_depthwise/depthwise_weights (3x3x512x1, 4.61k/4.61k params)

FeatureExtractor/MobilenetV1/Conv2d_12_pointwise (--/524.29k params)

FeatureExtractor/MobilenetV1/Conv2d_12_pointwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_12_pointwise/weights (1x1x512x1024, 524.29k/524.29k params)

FeatureExtractor/MobilenetV1/Conv2d_13_depthwise (--/9.22k params)

FeatureExtractor/MobilenetV1/Conv2d_13_depthwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_13_depthwise/depthwise_weights (3x3x1024x1, 9.22k/9.22k params)

FeatureExtractor/MobilenetV1/Conv2d_13_pointwise (--/1.05m params)

FeatureExtractor/MobilenetV1/Conv2d_13_pointwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_13_pointwise/weights (1x1x1024x1024, 1.05m/1.05m params)

FeatureExtractor/MobilenetV1/Conv2d_1_depthwise (--/288 params)

FeatureExtractor/MobilenetV1/Conv2d_1_depthwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_1_depthwise/depthwise_weights (3x3x32x1, 288/288 params)

FeatureExtractor/MobilenetV1/Conv2d_1_pointwise (--/2.05k params)

FeatureExtractor/MobilenetV1/Conv2d_1_pointwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_1_pointwise/weights (1x1x32x64, 2.05k/2.05k params)

FeatureExtractor/MobilenetV1/Conv2d_2_depthwise (--/576 params)

FeatureExtractor/MobilenetV1/Conv2d_2_depthwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_2_depthwise/depthwise_weights (3x3x64x1, 576/576 params)

FeatureExtractor/MobilenetV1/Conv2d_2_pointwise (--/8.19k params)

FeatureExtractor/MobilenetV1/Conv2d_2_pointwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_2_pointwise/weights (1x1x64x128, 8.19k/8.19k params)

FeatureExtractor/MobilenetV1/Conv2d_3_depthwise (--/1.15k params)

FeatureExtractor/MobilenetV1/Conv2d_3_depthwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_3_depthwise/depthwise_weights (3x3x128x1, 1.15k/1.15k params)

FeatureExtractor/MobilenetV1/Conv2d_3_pointwise (--/16.38k params)

FeatureExtractor/MobilenetV1/Conv2d_3_pointwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_3_pointwise/weights (1x1x128x128, 16.38k/16.38k params)

FeatureExtractor/MobilenetV1/Conv2d_4_depthwise (--/1.15k params)

FeatureExtractor/MobilenetV1/Conv2d_4_depthwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_4_depthwise/depthwise_weights (3x3x128x1, 1.15k/1.15k params)

FeatureExtractor/MobilenetV1/Conv2d_4_pointwise (--/32.77k params)

FeatureExtractor/MobilenetV1/Conv2d_4_pointwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_4_pointwise/weights (1x1x128x256, 32.77k/32.77k params)

FeatureExtractor/MobilenetV1/Conv2d_5_depthwise (--/2.30k params)

FeatureExtractor/MobilenetV1/Conv2d_5_depthwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_5_depthwise/depthwise_weights (3x3x256x1, 2.30k/2.30k params)

FeatureExtractor/MobilenetV1/Conv2d_5_pointwise (--/65.54k params)

FeatureExtractor/MobilenetV1/Conv2d_5_pointwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_5_pointwise/weights (1x1x256x256, 65.54k/65.54k params)

FeatureExtractor/MobilenetV1/Conv2d_6_depthwise (--/2.30k params)

FeatureExtractor/MobilenetV1/Conv2d_6_depthwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_6_depthwise/depthwise_weights (3x3x256x1, 2.30k/2.30k params)

FeatureExtractor/MobilenetV1/Conv2d_6_pointwise (--/131.07k params)

FeatureExtractor/MobilenetV1/Conv2d_6_pointwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_6_pointwise/weights (1x1x256x512, 131.07k/131.07k params)

FeatureExtractor/MobilenetV1/Conv2d_7_depthwise (--/4.61k params)

FeatureExtractor/MobilenetV1/Conv2d_7_depthwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_7_depthwise/depthwise_weights (3x3x512x1, 4.61k/4.61k params)

FeatureExtractor/MobilenetV1/Conv2d_7_pointwise (--/262.14k params)

FeatureExtractor/MobilenetV1/Conv2d_7_pointwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_7_pointwise/weights (1x1x512x512, 262.14k/262.14k params)

FeatureExtractor/MobilenetV1/Conv2d_8_depthwise (--/4.61k params)

FeatureExtractor/MobilenetV1/Conv2d_8_depthwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_8_depthwise/depthwise_weights (3x3x512x1, 4.61k/4.61k params)

FeatureExtractor/MobilenetV1/Conv2d_8_pointwise (--/262.14k params)

FeatureExtractor/MobilenetV1/Conv2d_8_pointwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_8_pointwise/weights (1x1x512x512, 262.14k/262.14k params)

FeatureExtractor/MobilenetV1/Conv2d_9_depthwise (--/4.61k params)

FeatureExtractor/MobilenetV1/Conv2d_9_depthwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_9_depthwise/depthwise_weights (3x3x512x1, 4.61k/4.61k params)

FeatureExtractor/MobilenetV1/Conv2d_9_pointwise (--/262.14k params)

FeatureExtractor/MobilenetV1/Conv2d_9_pointwise/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/Conv2d_9_pointwise/weights (1x1x512x512, 262.14k/262.14k params)

FeatureExtractor/MobilenetV1/fpn (--/2.82m params)

FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_14 (--/589.82k params)

FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_14/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_14/weights (3x3x256x256, 589.82k/589.82k params)

FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_15 (--/589.82k params)

FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_15/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/fpn/bottom_up_Conv2d_15/weights (3x3x256x256, 589.82k/589.82k params)

FeatureExtractor/MobilenetV1/fpn/projection_1 (--/65.79k params)

FeatureExtractor/MobilenetV1/fpn/projection_1/biases (256, 256/256 params)

FeatureExtractor/MobilenetV1/fpn/projection_1/weights (1x1x256x256, 65.54k/65.54k params)

FeatureExtractor/MobilenetV1/fpn/projection_2 (--/131.33k params)

FeatureExtractor/MobilenetV1/fpn/projection_2/biases (256, 256/256 params)

FeatureExtractor/MobilenetV1/fpn/projection_2/weights (1x1x512x256, 131.07k/131.07k params)

FeatureExtractor/MobilenetV1/fpn/projection_3 (--/262.40k params)

FeatureExtractor/MobilenetV1/fpn/projection_3/biases (256, 256/256 params)

FeatureExtractor/MobilenetV1/fpn/projection_3/weights (1x1x1024x256, 262.14k/262.14k params)

FeatureExtractor/MobilenetV1/fpn/smoothing_1 (--/589.82k params)

FeatureExtractor/MobilenetV1/fpn/smoothing_1/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/fpn/smoothing_1/weights (3x3x256x256, 589.82k/589.82k params)

FeatureExtractor/MobilenetV1/fpn/smoothing_2 (--/589.82k params)

FeatureExtractor/MobilenetV1/fpn/smoothing_2/BatchNorm (--/0 params)

FeatureExtractor/MobilenetV1/fpn/smoothing_2/weights (3x3x256x256, 589.82k/589.82k params)

WeightSharedConvolutionalBoxPredictor (--/4.87m params)

WeightSharedConvolutionalBoxPredictor/BoxPredictionTower (--/2.36m params)

WeightSharedConvolutionalBoxPredictor/BoxPredictionTower/conv2d_0 (--/589.82k params)

WeightSharedConvolutionalBoxPredictor/BoxPredictionTower/conv2d_0/BatchNorm (--/0 params)

WeightSharedConvolutionalBoxPredictor/BoxPredictionTower/conv2d_0/weights (3x3x256x256, 589.82k/589.82k params)

WeightSharedConvolutionalBoxPredictor/BoxPredictionTower/conv2d_1 (--/589.82k params)

WeightSharedConvolutionalBoxPredictor/BoxPredictionTower/conv2d_1/BatchNorm (--/0 params)

WeightSharedConvolutionalBoxPredictor/BoxPredictionTower/conv2d_1/weights (3x3x256x256, 589.82k/589.82k params)

WeightSharedConvolutionalBoxPredictor/BoxPredictionTower/conv2d_2 (--/589.82k params)

WeightSharedConvolutionalBoxPredictor/BoxPredictionTower/conv2d_2/BatchNorm (--/0 params)

WeightSharedConvolutionalBoxPredictor/BoxPredictionTower/conv2d_2/weights (3x3x256x256, 589.82k/589.82k params)

WeightSharedConvolutionalBoxPredictor/BoxPredictionTower/conv2d_3 (--/589.82k params)

WeightSharedConvolutionalBoxPredictor/BoxPredictionTower/conv2d_3/BatchNorm (--/0 params)

WeightSharedConvolutionalBoxPredictor/BoxPredictionTower/conv2d_3/weights (3x3x256x256, 589.82k/589.82k params)

WeightSharedConvolutionalBoxPredictor/BoxPredictor (--/55.32k params)

WeightSharedConvolutionalBoxPredictor/BoxPredictor/biases (24, 24/24 params)

WeightSharedConvolutionalBoxPredictor/BoxPredictor/weights (3x3x256x24, 55.30k/55.30k params)

WeightSharedConvolutionalBoxPredictor/ClassPredictionTower (--/2.36m params)

WeightSharedConvolutionalBoxPredictor/ClassPredictionTower/conv2d_0 (--/589.82k params)

WeightSharedConvolutionalBoxPredictor/ClassPredictionTower/conv2d_0/BatchNorm (--/0 params)

WeightSharedConvolutionalBoxPredictor/ClassPredictionTower/conv2d_0/weights (3x3x256x256, 589.82k/589.82k params)

WeightSharedConvolutionalBoxPredictor/ClassPredictionTower/conv2d_1 (--/589.82k params)

WeightSharedConvolutionalBoxPredictor/ClassPredictionTower/conv2d_1/BatchNorm (--/0 params)

WeightSharedConvolutionalBoxPredictor/ClassPredictionTower/conv2d_1/weights (3x3x256x256, 589.82k/589.82k params)

WeightSharedConvolutionalBoxPredictor/ClassPredictionTower/conv2d_2 (--/589.82k params)

WeightSharedConvolutionalBoxPredictor/ClassPredictionTower/conv2d_2/BatchNorm (--/0 params)

WeightSharedConvolutionalBoxPredictor/ClassPredictionTower/conv2d_2/weights (3x3x256x256, 589.82k/589.82k params)

WeightSharedConvolutionalBoxPredictor/ClassPredictionTower/conv2d_3 (--/589.82k params)

WeightSharedConvolutionalBoxPredictor/ClassPredictionTower/conv2d_3/BatchNorm (--/0 params)

WeightSharedConvolutionalBoxPredictor/ClassPredictionTower/conv2d_3/weights (3x3x256x256, 589.82k/589.82k params)

WeightSharedConvolutionalBoxPredictor/ClassPredictor (--/96.81k params)

WeightSharedConvolutionalBoxPredictor/ClassPredictor/biases (42, 42/42 params)

WeightSharedConvolutionalBoxPredictor/ClassPredictor/weights (3x3x256x42, 96.77k/96.77k params)

 

======================End of Report==========================

156 ops no flops stats due to incomplete shapes.

Parsing Inputs...

Incomplete shape.

 

=========================Options=============================

-max_depth 10000

-min_bytes 0

-min_peak_bytes 0

-min_residual_bytes 0

-min_output_bytes 0

-min_micros 0

-min_accelerator_micros 0

-min_cpu_micros 0

-min_params 0

-min_float_ops 1

-min_occurrence 0

-step -1

-order_by float_ops

-account_type_regexes .*

-start_name_regexes .*

-trim_name_regexes .*BatchNorm.*,.*Initializer.*,.*Regularizer.*,.*BiasAdd.*

-show_name_regexes .*

-hide_name_regexes

-account_displayed_op_only true

-select float_ops

-output stdout:

 

==================Model Analysis Report======================

Incomplete shape.

 

Doc:

scope: The nodes in the model graph are organized by their names, which is hierarchical like filesystem.

flops: Number of float operations. Note: Please read the implementation for the math behind it.

 

Profile:

node name | # float_ops

_TFProfRoot (--/512.01k flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator/mul_5 (76.80k/76.80k flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator/mul_6 (76.80k/76.80k flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator/sub (76.80k/76.80k flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates/Scale/mul_3 (38.40k/38.40k flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates/Scale/mul_2 (38.40k/38.40k flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates/Scale/mul_1 (38.40k/38.40k flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates/Scale/mul (38.40k/38.40k flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_1/mul_5 (19.20k/19.20k flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_1/mul_6 (19.20k/19.20k flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_1/sub (19.20k/19.20k flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_1/Scale/mul_3 (9.60k/9.60k flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_1/Scale/mul_2 (9.60k/9.60k flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_1/Scale/mul_1 (9.60k/9.60k flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_1/Scale/mul (9.60k/9.60k flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_2/sub (4.80k/4.80k flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_2/mul_6 (4.80k/4.80k flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_2/mul_5 (4.80k/4.80k flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_2/Scale/mul_2 (2.40k/2.40k flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_2/Scale/mul_1 (2.40k/2.40k flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_2/Scale/mul (2.40k/2.40k flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_2/Scale/mul_3 (2.40k/2.40k flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_3/sub (1.20k/1.20k flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_3/mul_6 (1.20k/1.20k flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_3/mul_5 (1.20k/1.20k flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_3/Scale/mul_3 (600/600 flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_3/Scale/mul (600/600 flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_3/Scale/mul_1 (600/600 flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_3/Scale/mul_2 (600/600 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_4/sub (300/300 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_4/mul_6 (300/300 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_4/mul_5 (300/300 flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_4/Scale/mul_3 (150/150 flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_4/Scale/mul_1 (150/150 flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_4/Scale/mul_2 (150/150 flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_4/Scale/mul (150/150 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator/mul_3 (80/80 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator/mul_4 (80/80 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_1/mul_3 (40/40 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_1/mul_4 (40/40 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_2/mul_4 (20/20 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_2/mul_3 (20/20 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_3/mul_3 (10/10 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_3/mul_4 (10/10 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_4/mul_2 (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_3/mul_1 (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_4/mul_1 (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_4/mul (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_3/truediv (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_4/truediv (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_1/truediv (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_1/mul_2 (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_1/mul_1 (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_1/mul (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_3/mul_2 (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_3/mul (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_2/truediv (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator/truediv (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_2/mul (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_2/mul_1 (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_2/mul_2 (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator/mul_2 (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator/mul_1 (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator/mul (6/6 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_4/mul_3 (5/5 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_4/mul_4 (5/5 flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_1/truediv_1 (1/1 flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_2/truediv (1/1 flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_2/truediv_1 (1/1 flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_1/truediv (1/1 flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates/truediv_1 (1/1 flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates/truediv (1/1 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator/assert_equal_1/Equal (1/1 flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_3/truediv (1/1 flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_3/truediv_1 (1/1 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_4/assert_equal_1/Equal (1/1 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_3/assert_equal_1/Equal (1/1 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_2/assert_equal_1/Equal (1/1 flops)

MultiscaleGridAnchorGenerator/GridAnchorGenerator_1/assert_equal_1/Equal (1/1 flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_4/truediv (1/1 flops)

MultiscaleGridAnchorGenerator/ToNormalizedCoordinates_4/truediv_1 (1/1 flops)

MultiscaleGridAnchorGenerator/assert_equal_1/Equal (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/Less (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/Less_1 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/ChangeCoordinateFrame/sub (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/ChangeCoordinateFrame/sub_1 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/ChangeCoordinateFrame/truediv (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/ChangeCoordinateFrame/truediv_1 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/Greater (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/Minimum (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/Minimum_1 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/Minimum_2 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/Minimum_3 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/Minimum_4 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/Minimum_5 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/Minimum_6 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/SortByField/Equal (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/SortByField_1/Equal (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/sub (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/sub_1 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/sub_10 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/sub_11 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/sub_2 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/sub_3 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/sub_4 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/sub_5 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/sub_6 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/sub_7 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/sub_8 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/MultiClassNonMaxSuppression/sub_9 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/Greater (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/Greater_1 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/Greater_2 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/Greater_3 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/Greater_4 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/Greater_5 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/Greater_6 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/Greater_7 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/Greater_8 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/Greater_9 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_1 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_10 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_11 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_12 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_13 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_14 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_15 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_16 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_17 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_18 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_19 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_2 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_3 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_4 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_5 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_6 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_7 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_8 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/sub_9 (1/1 flops)

Postprocessor/BatchMultiClassNonMaxSuppression/ones/Less (1/1 flops)

Preprocessor/map/while/Less (1/1 flops)

Preprocessor/map/while/Less_1 (1/1 flops)

 

======================End of Report==========================

2021-07-23 14:18:09.410538: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA

2021-07-23 14:18:09.483904: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fbff1a09270 initialized for platform Host (this does not guarantee that XLA will be used). Devices:

2021-07-23 14:18:09.483924: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version

INFO:tensorflow:Restoring parameters from /Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt-102537

I0723 14:18:09.490651 4487224832 saver.py:1284] Restoring parameters from /Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt-102537

WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/tools/freeze_graph.py:127: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.

Instructions for updating:

Use standard file APIs to check for files with this prefix.

W0723 14:18:12.144515 4487224832 deprecation.py:323] From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/tools/freeze_graph.py:127: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.

Instructions for updating:

Use standard file APIs to check for files with this prefix.

INFO:tensorflow:Restoring parameters from /Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt-102537

I0723 14:18:13.154244 4487224832 saver.py:1284] Restoring parameters from /Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt-102537

WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/tools/freeze_graph.py:233: convert_variables_to_constants (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version.

Instructions for updating:

Use `tf.compat.v1.graph_util.convert_variables_to_constants`

W0723 14:18:14.205757 4487224832 deprecation.py:323] From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/tools/freeze_graph.py:233: convert_variables_to_constants (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version.

Instructions for updating:

Use `tf.compat.v1.graph_util.convert_variables_to_constants`

WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/framework/graph_util_impl.py:277: extract_sub_graph (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version.

Instructions for updating:

Use `tf.compat.v1.graph_util.extract_sub_graph`

W0723 14:18:14.206080 4487224832 deprecation.py:323] From /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/framework/graph_util_impl.py:277: extract_sub_graph (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version.

Instructions for updating:

Use `tf.compat.v1.graph_util.extract_sub_graph`

INFO:tensorflow:Froze 333 variables.

I0723 14:18:14.853020 4487224832 graph_util_impl.py:334] Froze 333 variables.

INFO:tensorflow:Converted 333 variables to const ops.

I0723 14:18:15.042360 4487224832 graph_util_impl.py:394] Converted 333 variables to const ops.

WARNING:tensorflow:From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/exporter.py:384: build_tensor_info (from tensorflow.python.saved_model.utils_impl) is deprecated and will be removed in a future version.

Instructions for updating:

This function will only be available through the v1 compatibility library as tf.compat.v1.saved_model.utils.build_tensor_info or tf.compat.v1.saved_model.build_tensor_info.

W0723 14:18:16.424932 4487224832 deprecation.py:323] From /Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/exporter.py:384: build_tensor_info (from tensorflow.python.saved_model.utils_impl) is deprecated and will be removed in a future version.

Instructions for updating:

This function will only be available through the v1 compatibility library as tf.compat.v1.saved_model.utils.build_tensor_info or tf.compat.v1.saved_model.build_tensor_info.

INFO:tensorflow:No assets to save.

I0723 14:18:16.425487 4487224832 builder_impl.py:640] No assets to save.

INFO:tensorflow:No assets to write.

I0723 14:18:16.425562 4487224832 builder_impl.py:460] No assets to write.

INFO:tensorflow:SavedModel written to: /Users/emre/Documents/Temp/tensorflow_last/models/train/saved_model/saved_model.pb

I0723 14:18:17.382722 4487224832 builder_impl.py:425] SavedModel written to: /Users/emre/Documents/Temp/tensorflow_last/models/train/saved_model/saved_model.pb

INFO:tensorflow:Writing pipeline config file to /Users/emre/Documents/Temp/tensorflow_last/models/train/pipeline.config

I0723 14:18:17.437540 4487224832 config_util.py:254] Writing pipeline config file to /Users/emre/Documents/Temp/tensorflow_last/models/train/pipeline.config

 

Process finished with exit code 0

 

But the problem is that my model cannot detect objects properly. Although I have 6 items in my labelmap.txt,

It shows just 1th and/or 3th items as detected and detection is also totally wrong.

 

Ex: Although I am trying to detect human body parts, It detects texts in an artical as detected item 1 or 3.

 

Note:I am pretty sure that my training photos and photo labelings were correct since I used the same photos and photo labels

for faster_rcnn_inception_v2_coco_2018_01_28 model traning and the output was perfect.

(I used following website for the trainig and inference:

https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-W...)

 

The only thing which I modified for ssd_mobilenet_v1_fpn_coco training, was my pipline.config file and these files

(model.ckpt.data-00000-of-00001, model.ckpt.index and model.ckpt.meta which are downloaded by openvino downloader).

Do I miss any point? Could the reason of wrong detection be that I do not have proper nodes in my model?

 

Thank you very much in advance.

Syamimi_Intel
Moderator
960 Views

Hi Emre Gun,

Sorry for making you confused. If you run the original ssd_mobilenet_v1_fpn_coco model without doing any changes, you should be able to check input and output nodes within a model through the Netron model viewer. But after you train the model, we are not able to check the input and output nodes within a model through the Netron model viewer.

 

For your second question, can you please share your .pb file with us?

 

Regards,

Syamimi


emregun
New Contributor I
950 Views

Hi Syamimi,

 

Sure. PD. file is attached below.

 

Thanks a lot.

 

Best Regards

Emre

 

Syamimi_Intel
Moderator
942 Views

Hi Emre Gun,

Can you share your latest model with us ? Including pipeline.config and saved_model.pb. And what is the command that you used to convert the model ?

 

 

Regards,

Syamimi


emregun
New Contributor I
931 Views

Hi Syamimi,

 

This is my command:

Command:

/Users/emre/Documents/Temp/tensorflow_last/models/research/object_detection/object_detection/export_inference_graph.py

 

--input_type=image_tensor

--pipeline_config_path=/Users/emre/Documents/Temp/tensorflow_last/models/ssd_mobilenet_v1_fpn_shared_box_predictor_640x640_coco14_sync.config

--trained_checkpoint_prefix=/Users/emre/Documents/Temp/tensorflow_last/models/train/model.ckpt-98977

--output_directory=/Users/emre/Documents/Temp/tensorflow_last/models/train

 

And you can find all related files in following link:

https://www.dropbox.com/s/qauzt16ka59mtwj/train%204.zip?dl=0

 

Thanks a lot.

 

Best Regards

Emre

Syamimi_Intel
Moderator
902 Views

Hi Emre Gun,

Thank you for waiting, I have converted your model used the following command:

python mo_tf.py --output_dir="<INSTALL_DIR>\openvino_2021.4.582\deployment_tools\tools\model_downloader\public\yolocustom" --model_name=ssd_mobilenet_v1_fpn_coco --reverse_input_channels --input_shape=[1,640,640,3] --input=image_tensor --output=detection_scores,detection_boxes,num_detections --transformations_config="<INSTALL_DIR>\openvino_2021.4.582\deployment_tools\model_optimizer\extensions\front\tf\ssd_support_api_v1.15.json" --tensorflow_object_detection_api_pipeline_config="C:\Users\nursy71x\Downloads\train 4\train\pipeline.config" --input_model="C:\Users\nursy71x\Downloads\train 4\train\frozen_inference_graph.pb"

 

But I also received the same issue as you when I run the model with the Object Detection Demo. It did not detect the object properly.

 

I would suggest you train similar dimension images as in the test frames. Your train data has to be as similar as possible to your eval data, without entering the overfit zone. At least the images have to be of similar size and aspect ratio from the same domain.

 

Someone actually had an almost similar problem before, you can try checking at the following link:

https://stackoverflow.com/questions/49484066/tensorflow-object-detection-api-does-not-detect-objects...

 

 

Regards,

Syamimi


emregun
New Contributor I
824 Views

Hi Syamimi,

 

Thank you for the response. I will check it and let you know.

 

Have a nice day.

 

Emre

emregun
New Contributor I
820 Views

Hi Syamimi,

 

I am here again

 

So I guess I get your point. Could you please confirm if I get it right or wrong?

 

When I trained my model with faster_rcnn_inception_v2_coco_2018_01_28, It worked totally fine with 800X600 resized training photo images.

I guess the reason is that faster_rcnn_inception_v2_coco_2018_01_28 model allows the users to use a flexible training images size between 600 and 1024, as I found following variable in the pipeline config.

 

keep_aspect_ratio_resizer {
min_dimension: 600
max_dimension: 1024
}

 

But ssd_mobilenet_v2_quantized_300x300_coco_2019_01_03 model forces the users to use a fix photo image size for  training as 300x300. Which is also defined in pipeline config(and which I should recognise from the name of model ssd_mobilenet_v2_quantized_300x300_coco_2019_01_03 before I trained my model :D)

 

image_resizer {
fixed_shape_resizer {
height: 300
width: 300
}

 

So my questions:

 

1-If I get your point right, could you please tell me, is there any way to fix this problem without re-training the model? The training took almost 4 weeks, it was absolutely painful.

 

2-If there is no other way, can I just resize my photos(which were already resized before from original size to 800x600) to 300x300 and retrain my model ssd_mobilenet_v2_quantized_300x300_coco_2019_01_03 or do I have to find the original photos and re-size them again to 300x300? I guess they would loose quality, if I resize the photos which were already resized before.

 

Thanks a lot in advance.

 

Emre 

Reply