Community
cancel
Showing results for 
Search instead for 
Did you mean: 
qin__guiqiu
Beginner
114 Views

model optimizer for tensorflow model----faster_rcnn_inception_v2

Hi,

I have trained own tensorflow model--faster_rcnn_inception_v2's frozen model.pb

I tried to optimize the model with :

 python mo_tf.py --input_model /home/g2/model_frcnn_meta/frozen_inference_graph.pb --output_dir /home/g2/model_32 --tensorflow_use_custom_operations_config /opt/intel/openvino/deployment_tools/model_optimizer/extensions/front/tf/faster_rcnn_support.json --output="detection_boxes,detection_scores,num_detections" --tensorflow_object_detection_api_pipeline_config /home/g2/model_frcnn_meta/pipeline.config

But,I encountered a error blow:

Model Optimizer arguments:
Common parameters:
        - Path to the Input Model:      /home/g2/model_frcnn_meta/frozen_inference_graph.pb
        - Path for generated IR:        /home/g2/model_32
        - IR output name:       frozen_inference_graph
        - Log level:    ERROR
        - Batch:        Not specified, inherited from the model
        - Input layers:         Not specified, inherited from the model
        - Output layers:        detection_boxes,detection_scores,num_detections
        - 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:       False
        - 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:  /home/g2/model_frcnn_meta/pipeline.config
        - Operations to offload:        None
        - Patterns to offload:  None
        - Use the config file:  /opt/intel/openvino/deployment_tools/model_optimizer/extensions/front/tf/faster_rcnn_support.json
Model Optimizer version:        2019.3.0-408-gac8584cb7
[ WARNING ] Model Optimizer removes pre-processing block of the model which resizes image keeping aspect ratio. The Inference Engine does not support dynamic image size so the Intermediate Representation file is generated with the input image size of a fixed size.
Specify the "--input_shape" command line parameter to override the default shape which is equal to (600, 600).
The Preprocessor block has been removed. Only nodes performing mean value subtraction and scaling (if applicable) are kept.
[ ERROR ]  Failed to match nodes from custom replacement description with id 'ObjectDetectionAPIProposalReplacement':
It means model and custom replacement description are incompatible.
Try to correct custom replacement description according to documentation with respect to model node names
[ ERROR ]  Found the following nodes '[]' with name 'crop_proposals' but there should be exactly 1. Looks like ObjectDetectionAPIProposalReplacement replacement didn't work.
Exception occurred during running replacer "ObjectDetectionAPIDetectionOutputReplacement" (<class 'extensions.front.tf.ObjectDetectionAPI.ObjectDetectionAPIDetectionOutputReplacement'>): Found the following nodes '[]' with name 'crop_proposals' but there should be exactly 1. Looks like ObjectDetectionAPIProposalReplacement replacement didn't work.
 

This is my pipeline.config as below:

model { faster_rcnn { num_classes: 4 image_resizer { keep_aspect_ratio_resizer { min_dimension: 600 max_dimension: 1024 } } feature_extractor { type: "faster_rcnn_inception_v2" first_stage_features_stride: 16 } first_stage_anchor_generator { grid_anchor_generator { height_stride: 16 width_stride: 16 scales: 0.25 scales: 0.5 scales: 1.0 scales: 2.0 aspect_ratios: 0.5 aspect_ratios: 1.0 aspect_ratios: 2.0 } } first_stage_box_predictor_conv_hyperparams { op: CONV regularizer { l2_regularizer { weight: 0.0 } } initializer { truncated_normal_initializer { stddev: 0.009999999776482582 } } } first_stage_nms_score_threshold: 0.0 first_stage_nms_iou_threshold: 0.699999988079071 first_stage_max_proposals: 100 first_stage_localization_loss_weight: 2.0 first_stage_objectness_loss_weight: 1.0 initial_crop_size: 14 maxpool_kernel_size: 2 maxpool_stride: 2 second_stage_box_predictor { mask_rcnn_box_predictor { fc_hyperparams { op: FC regularizer { l2_regularizer { weight: 0.0 } } initializer { variance_scaling_initializer { factor: 1.0 uniform: true mode: FAN_AVG } } } use_dropout: false dropout_keep_probability: 1.0 } } second_stage_post_processing { batch_non_max_suppression { score_threshold: 0.30000001192092896 iou_threshold: 0.6000000238418579 max_detections_per_class: 100 max_total_detections: 100 } score_converter: SOFTMAX } second_stage_localization_loss_weight: 2.0 second_stage_classification_loss_weight: 1.0 } } train_config { batch_size: 1 data_augmentation_options { random_horizontal_flip { } } optimizer { momentum_optimizer { learning_rate { manual_step_learning_rate { initial_learning_rate: 0.00019999999494757503 schedule { step: 1 learning_rate: 0.00019999999494757503 } schedule { step: 900000 learning_rate: 1.9999999494757503e-05 } schedule { step: 1200000 learning_rate: 1.9999999949504854e-06 } } } momentum_optimizer_value: 0.8999999761581421 } use_moving_average: false } gradient_clipping_by_norm: 10.0 fine_tune_checkpoint: "/mnt/hdd1/zx/tensorflow-research/work/logdir/model.ckpt" from_detection_checkpoint: true num_steps: 200000 } train_input_reader { label_map_path: "/home/g2/model_frcnn_meta/pascal_label_map.pbtxt" tf_record_input_reader { input_path: "/mnt/hdd1/zx/samples/VOCdevkit/VOC2007/record/pascal_train.record" } } eval_config { num_examples: 8000 max_evals: 10 use_moving_averages: false } eval_input_reader { label_map_path: "/home/g2/model_frcnn_meta/pascal_label_map.pbtxt" shuffle: false num_readers: 1 tf_record_input_reader { input_path: "/mnt/hdd1/zx/samples/VOCdevkit/VOC2007/record/pascal_val.record" } }

Someone have idea how I can solve the problem ? Thank you for your advance .

 

 

0 Kudos
0 Replies
Reply