Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.
6392 Discussions

Error running IR Model on Neural Compute Stick

Bartyzel__Grzegorz
884 Views

Hi,

I'm trying to get started with OpenVINO and Neural Compute Stick. For "Hello world" task I chose converting one of my Tensorflow Model to IR Model and run it on NCS. The model is http://download.tensorflow.org/models/object_detection/faster_rcnn_resnet101_coco_2018_01_28.tar.gz (from Tensorflow Model Zoo Object Detection). Of course I'm using it with custom classes and input shape. Compilation to IR Model works like a charm (FP16 and FP32):

python3 mo_tf.py --input_meta_graph ~/train_09_07/model.ckpt-66967.meta --tensorflow_use_custom_operations_config extensions/front/tf/faster_rcnn_support_api_v1.7.json --tensorflow_object_detection_api_pipeline_config ~/train_09_07/pipeline.config --reverse_input_channels --data_type FP32 --batch 1

First for execution I'm using object_detection_sample_ssd from samples delivered with OpenVINO. On CPU execution works. However, when I'm trying to run this on NCS (with model converted to FP16) following error appears:

[ ERROR ] [VPU] Reshape input or output reshape_4d has invalid batch

I was trying to change batch size etc. but nothing works.

I will be grateful for any help.

Greg

0 Kudos
8 Replies
Monique_J_Intel
Employee
884 Views

Hi Grzegorz,

Using just the meta graph file isn't enough to convert the model I will reproduce your issue on my side and supply the command line for you to use.

Kind Regards,

Monique Jones

0 Kudos
Monique_J_Intel
Employee
884 Views

Hi Grzegorz,

I converted the model with the following command please give it a try:

sudo python3 /opt/intel/computer_vision_sdk/deployment_tools/model_optimizer/mo.py --input_model frozen_inference_graph.pb --tensorflow_object_detection_api_pipeline_config pipeline.config  --output="detection_boxes,detection_scores,num_detections" --tensorflow_use_custom_operations_config /opt/intel/computer_vision_sdk/deployment_tools/model_optimizer/extensions/front/tf/faster_rcnn_support_api_v1.7.json.json

I will try to run it on NCS and see if I get the same error.

Kind Regards,

Monique Jones

0 Kudos
Monique_J_Intel
Employee
884 Views

Ok so everything works well on CPU as you saw as well. With the movidius stick i'm getting the following error

[ ERROR ] [VPU] input SecondStageFeatureExtractor/resnet_v1_101/block4/unit_1/bottleneck_v1/add has invalid batc

let me take troubleshoot this a bit further and take a look at the graph and see what batch size it's expecting for this layer.

FYI I converted the model again with extra parameters data_type FP16, --batch 1, and --tensorboard_logdir

Kind Regards,

Monique Jones

0 Kudos
Garolla__Filippo
Beginner
884 Views

Hello, I'm running into the same problem. Was this issue solved?

0 Kudos
Berrefas__Thiziri
884 Views

Hello,

I tried to convert models mask_rcnn from TensorFlow Object Detection Models Zoo using this command:

mo_tf.py --input_model $ / rcnn_bis / mask_rcnn_resnet101_atrous_coco_2018_01_28 / frozen_inference_graph.pb --tensorflow_use_custom_operations_config /opt/intel/computer_vision_sdk/deployment_tools/model_optimizer/extensions/front/tf/mask_rcnn_support.json --tensorflow_object_detection_api_pipeline_config $ / mask_rcnn_resnet101_atrous_coco_2018_01_28 / pipeline.config - data_type FP16 --batch 1

And I wanted to launch an inference with the following command using an input image of 960 * 525

./mask_rcnn_demo -i $ / blue_car_W_960_H_525.png -m $ / mask_rcnn_resnet101_atrous_coco_2018_01_28 / FP16 / frozen_inference_graph.xml -d MYRIAD

In output I had this error

[ERROR] [VPU] Input SecondStageBoxPredictor_1 / ResizeBilinear has invalid batch

I also converted the rfcn models using this command

mo_tf.py --input_model $ / rfcn_resnet101_coco_2018_01_28 / frozen_inference_graph.pb --tensorflow_use_custom_operations_config /opt/intel/computer_vision_sdk/deployment_tools/model_optimizer/extensions/front/tf/rfcn_support.json --tensorflow_object_detection_api_pipeline_config $ / rfcn_resnet101_coco_2018_01_28 / pipeline.config --data_type FP16 --batch 1

for the inference I used the following command:

./segmentation_demo -i $ / blue_car_W_960_H_525.png -m $ / rfcn_resnet101_coco_2018_01_28 / FP32 / frozen_inference_graph.xml -d MYRIAD

And I had this error

[ERROR] vector :: _ M_range_check: __n (which is 18446744073709551615)> = this-> size () (which is 21)

Can you tell me what to do to fix these errors.

Thanking you in advance.

Thiziri

 

 

0 Kudos
Shubha_R_Intel
Employee
884 Views

Dear Thiziri:

I'm currently looking into your issues. Sorry that you're having difficulties ! Can you clarify what you mean by this statement ?

Of course I'm using it with custom classes and input shape.

Also I have PM'd you, so that you can zip up your frozen.pb and send it to me privately. 

Thanks for using OpenVino !

Shubha

0 Kudos
Shubha_R_Intel
Employee
884 Views

Dear Thiziri (and everyone):

I encourage you to download the latest release of OpenVino 2019 R1, released today. In this release I see a mask_rcnn_support.json, mask_rcnn_support_api_v1.7.json and mask_rcnn_support_api_v1.11.json.  I also see rfcn_support.json and rfcn_support_api_v1.10.json.  Note that rfcn_support_api_v1.10.json is new in OpenVino 2019 R1. It's important to match up the *.json version number with the Tensorflow API version number. Here is exact wording from the MO Object Detection Online Document:

mask_rcnn_support.json — for frozen Mask R-CNN topologies from the models zoo

mask_rcnn_support_api_v1.7.json — for Mask R-CNN topologies trained manually using the TensorFlow* Object Detection API version 1.7.0 or higher up to 1.9.0 inclusively

mask_rcnn_support_api_v1.11.json — for Mask R-CNN topologies trained manually using the TensorFlow* Object Detection API version 1.10.0 or higher

rfcn_support.json — for the frozen RFCN topology from the models zoo frozen with TensorFlow* version 1.9.0 or lower.

rfcn_support_api_v1.10.json — for the frozen RFCN topology from the models zoo frozen with TensorFlow* version 1.10.0 or higher.

If you follow these rules, model conversion should work. If it still fails however, please feel free to post here and we will help out !

Thanks for using OpenVino !

Shubha

0 Kudos
Berrefas__Thiziri
884 Views

Hi Shubha,

Thank you for your help and for the news. I will try again with this information. And I hope it will work!

Regards,
Thiziri

0 Kudos
Reply