### 2-1. MobileNetV3+DeeplabV3+PascalVOC #### 2-1-1. Preparation ```bash $ cd ~ $ mkdir deeplab;cd deeplab $ git clone --depth 1 https://github.com/tensorflow/models.git $ cd models/research/deeplab/datasets $ mkdir pascal_voc_seg $ curl -sc /tmp/cookie \ "https://drive.google.com/uc?export=download&id=1rATNHizJdVHnaJtt-hW9MOgjxoaajzdh" > /dev/null $ CODE="$(awk '/_warning_/ {print $NF}' /tmp/cookie)" $ curl -Lb /tmp/cookie \ "https://drive.google.com/uc?export=download&confirm=${CODE}&id=1rATNHizJdVHnaJtt-hW9MOgjxoaajzdh" \ -o pascal_voc_seg/VOCtrainval_11-May-2012.tar $ sed -i -e "s/python .\/remove_gt_colormap.py/python3 .\/remove_gt_colormap.py/g" \ -i -e "s/python .\/build_voc2012_data.py/python3 .\/build_voc2012_data.py/g" \ download_and_convert_voc2012.sh $ sh download_and_convert_voc2012.sh $ cd ../.. $ mkdir -p deeplab/datasets/pascal_voc_seg/exp/train_on_train_set/train $ mkdir -p deeplab/datasets/pascal_voc_seg/exp/train_on_train_set/eval $ mkdir -p deeplab/datasets/pascal_voc_seg/exp/train_on_train_set/vis $ export PATH_TO_TRAIN_DIR=${HOME}/deeplab/models/research/deeplab/datasets/pascal_voc_seg/exp/train_on_train_set/train $ export PATH_TO_DATASET=${HOME}/deeplab/models/research/deeplab/datasets/pascal_voc_seg/tfrecord $ export PYTHONPATH=${HOME}/deeplab/models/research:${HOME}/deeplab/models/research/deeplab:${HOME}/deeplab/models/research/slim:${PYTHONPATH} ``` ```python # See feature_extractor.network_map for supported model variants. # models/research/deeplab/core/feature_extractor.py networks_map = { 'mobilenet_v2': _mobilenet_v2, 'mobilenet_v3_large_seg': mobilenet_v3_large_seg, 'mobilenet_v3_small_seg': mobilenet_v3_small_seg, 'resnet_v1_18': resnet_v1_beta.resnet_v1_18, 'resnet_v1_18_beta': resnet_v1_beta.resnet_v1_18_beta, 'resnet_v1_50': resnet_v1_beta.resnet_v1_50, 'resnet_v1_50_beta': resnet_v1_beta.resnet_v1_50_beta, 'resnet_v1_101': resnet_v1_beta.resnet_v1_101, 'resnet_v1_101_beta': resnet_v1_beta.resnet_v1_101_beta, 'xception_41': xception.xception_41, 'xception_65': xception.xception_65, 'xception_71': xception.xception_71, 'nas_pnasnet': nas_network.pnasnet, 'nas_hnasnet': nas_network.hnasnet, } ``` #### 2-1-2. "mobilenet_v3_small_seg" Float32 regular training ```bash $ python3 deeplab/train.py \ --logtostderr \ --training_number_of_steps=500000 \ --train_split="train" \ --model_variant="mobilenet_v3_small_seg" \ --decoder_output_stride=16 \ --train_crop_size="513,513" \ --train_batch_size=8 \ --dataset="pascal_voc_seg" \ --save_interval_secs=300 \ --save_summaries_secs=300 \ --save_summaries_images=True \ --log_steps=100 \ --train_logdir=${PATH_TO_TRAIN_DIR} \ --dataset_dir=${PATH_TO_DATASET} ``` #### 2-1-3. "mobilenet_v3_large_seg" Float32 regular training ```bash $ python3 deeplab/train.py \ --logtostderr \ --training_number_of_steps=1000000 \ --train_split="train" \ --model_variant="mobilenet_v3_large_seg" \ --decoder_output_stride=16 \ --train_crop_size="513,513" \ --train_batch_size=8 \ --dataset="pascal_voc_seg" \ --save_interval_secs=300 \ --save_summaries_secs=300 \ --save_summaries_images=True \ --log_steps=100 \ --train_logdir=${PATH_TO_TRAIN_DIR} \ --dataset_dir=${PATH_TO_DATASET} ``` #### 2-1-4. Visualize training status ```bash $ tensorboard \ --logdir ${HOME}/deeplab/models/research/deeplab/datasets/pascal_voc_seg/exp/train_on_train_set/train ``` 　 　 ### 2-2. MobileNetV3+DeeplabV3+Cityscaps - Post-training quantization #### 2-2-1. Preparation ```bash $ cd ~ $ mkdir -p git/deeplab && cd git/deeplab $ git clone --depth 1 https://github.com/tensorflow/models.git $ cd models/research/deeplab/datasets $ mkdir cityscapes && cd cityscapes # Clone the script to generate Cityscapes Dataset. $ git clone --depth 1 https://github.com/mcordts/cityscapesScripts.git $ mv cityscapesScripts cityscapesScripts_ && \ mv cityscapesScripts_/cityscapesscripts . && \ rm -rf cityscapesScripts_ # Download Cityscapes Dataset. # https://www.cityscapes-dataset.com/ # You will need to sign up and issue a userID and password to download the data set. $ wget --keep-session-cookies --save-cookies=cookies.txt \ --post-data 'username=(userid)&password=(password)&submit=Login' \ https://www.cityscapes-dataset.com/login/ $ wget --load-cookies cookies.txt \ --content-disposition https://www.cityscapes-dataset.com/file-handling/?packageID=1 $ wget --load-cookies cookies.txt \ --content-disposition https://www.cityscapes-dataset.com/file-handling/?packageID=3 $ unzip gtFine_trainvaltest.zip && rm gtFine_trainvaltest.zip $ rm README && rm license.txt $ unzip leftImg8bit_trainvaltest.zip && rm leftImg8bit_trainvaltest.zip $ rm README && rm license.txt # Convert Cityscapes Dataset to TFRecords format. $ cd .. $ sed -i -e "s/python/python3/g" convert_cityscapes.sh $ export PYTHONPATH=${HOME}/git/deeplab/models/research/deeplab/datasets/cityscapes:${PYTHONPATH} $ sh convert_cityscapes.sh # Create a checkpoint storage folder for training. If training is not required, # there is no need to carry out. $ cd ../.. $ mkdir -p deeplab/datasets/cityscapes/exp/train_on_train_set/train && \ mkdir -p deeplab/datasets/cityscapes/exp/train_on_train_set/eval && \ mkdir -p deeplab/datasets/cityscapes/exp/train_on_train_set/vis # Download the DeepLabV3 trained model of the MobileNetV3 backbone. $ curl -sc /tmp/cookie \ "https://drive.google.com/uc?export=download&id=1f5ccaJmJBYwBmHvRQ77yGIUcXnqQIRY_" > /dev/null $ CODE="$(awk '/_warning_/ {print $NF}' /tmp/cookie)" $ curl -Lb /tmp/cookie \ "https://drive.google.com/uc?export=download&confirm=${CODE}&id=1f5ccaJmJBYwBmHvRQ77yGIUcXnqQIRY_" \ -o deeplab_mnv3_small_cityscapes_trainfine_2019_11_15.tar.gz $ tar -zxvf deeplab_mnv3_small_cityscapes_trainfine_2019_11_15.tar.gz $ rm deeplab_mnv3_small_cityscapes_trainfine_2019_11_15.tar.gz $ curl -sc /tmp/cookie \ "https://drive.google.com/uc?export=download&id=1QxS3G55rUQvuiBF-hztQv5zCkfPfwlVU" > /dev/null $ CODE="$(awk '/_warning_/ {print $NF}' /tmp/cookie)" $ curl -Lb /tmp/cookie \ "https://drive.google.com/uc?export=download&confirm=${CODE}&id=1QxS3G55rUQvuiBF-hztQv5zCkfPfwlVU" \ -o deeplab_mnv3_large_cityscapes_trainfine_2019_11_15.tar.gz $ tar -zxvf deeplab_mnv3_large_cityscapes_trainfine_2019_11_15.tar.gz $ rm deeplab_mnv3_large_cityscapes_trainfine_2019_11_15.tar.gz $ export PATH_TO_INITIAL_CHECKPOINT=${HOME}/git/deeplab/models/research/deeplab_mnv3_small_cityscapes_trainfine/model.ckpt $ export PATH_TO_DATASET=${HOME}/git/deeplab/models/research/deeplab/datasets/cityscapes/tfrecord $ export PYTHONPATH=${HOME}/git/deeplab/models/research:${HOME}/git/deeplab/models/research/deeplab:${HOME}/git/deeplab/models/research/slim:${PYTHONPATH} # Fix a bug in the data generator. $ sed -i -e \ "s/splits_to_sizes={'train_fine': 2975,/splits_to_sizes={'train': 2975,/g" \ deeplab/datasets/data_generator.py # Back up the trained model. $ cd ${HOME}/git/deeplab/models/research $ cp deeplab/export_model.py deeplab/export_model.py_org $ cp deeplab_mnv3_small_cityscapes_trainfine/frozen_inference_graph.pb \ deeplab_mnv3_small_cityscapes_trainfine/frozen_inference_graph_org.pb $ cp deeplab_mnv3_large_cityscapes_trainfine/frozen_inference_graph.pb \ deeplab_mnv3_large_cityscapes_trainfine/frozen_inference_graph_org.pb # Customize "export_model.py" according to the input resolution. Must be (multiple of 8 + 1). # (example.1) 769 = 8 * 96 + 1 # (example.2) 512 = 8 * 64 + 1 # (example.3) 320 = 8 * 40 + 1 # And it is necessary to change from tf.uint8 type to tf.float32 type. $ sed -i -e \ "s/tf.placeholder(tf.uint8, \[1, None, None, 3\], name=_INPUT_NAME)/tf.placeholder(tf.float32, \[1, 769, 769, 3\], name=_INPUT_NAME)/g" \ deeplab/export_model.py ``` #### 2-2-2. Parameter sheet ```bash # crop_size and image_pooling_crop_size are multiples of --decoder_output_stride + 1 # 769 = 8 * 96 + 1 # 513 = 8 * 64 + 1 # 321 = 8 * 40 + 1 # --initialize_last_layer=True initializes the final layer with the weight of # tf_initial_checkpoint (inherits the weight) # Named tuple to describe the dataset properties. # deeplab/datasets/data_generator.py DatasetDescriptor = collections.namedtuple( 'DatasetDescriptor', [ 'splits_to_sizes', # Splits of the dataset into training, val and test. 'num_classes', # Number of semantic classes, including the # background class (if exists). For example, there # are 20 foreground classes + 1 background class in # the PASCAL VOC 2012 dataset. Thus, we set # num_classes=21. 'ignore_label', # Ignore label value. ]) _CITYSCAPES_INFORMATION = DatasetDescriptor( splits_to_sizes={'train': 2975, 'train_coarse': 22973, 'trainval_fine': 3475, 'trainval_coarse': 23473, 'val_fine': 500, 'test_fine': 1525}, num_classes=19, ignore_label=255, ) _PASCAL_VOC_SEG_INFORMATION = DatasetDescriptor( splits_to_sizes={ 'train': 1464, 'train_aug': 10582, 'trainval': 2913, 'val': 1449, }, num_classes=21, ignore_label=255, ) _ADE20K_INFORMATION = DatasetDescriptor( splits_to_sizes={ 'train': 20210, # num of samples in images/training 'val': 2000, # num of samples in images/validation }, num_classes=151, ignore_label=0, ) _DATASETS_INFORMATION = { 'cityscapes': _CITYSCAPES_INFORMATION, 'pascal_voc_seg': _PASCAL_VOC_SEG_INFORMATION, 'ade20k': _ADE20K_INFORMATION, } # A map from network name to network function. model_variant. # deeplab/core/feature_extractor.py networks_map = { 'mobilenet_v2': _mobilenet_v2, 'mobilenet_v3_large_seg': mobilenet_v3_large_seg, 'mobilenet_v3_small_seg': mobilenet_v3_small_seg, 'resnet_v1_18': resnet_v1_beta.resnet_v1_18, 'resnet_v1_18_beta': resnet_v1_beta.resnet_v1_18_beta, 'resnet_v1_50': resnet_v1_beta.resnet_v1_50, 'resnet_v1_50_beta': resnet_v1_beta.resnet_v1_50_beta, 'resnet_v1_101': resnet_v1_beta.resnet_v1_101, 'resnet_v1_101_beta': resnet_v1_beta.resnet_v1_101_beta, 'xception_41': xception.xception_41, 'xception_65': xception.xception_65, 'xception_71': xception.xception_71, 'nas_pnasnet': nas_network.pnasnet, 'nas_hnasnet': nas_network.hnasnet, } ``` #### 2-2-3. "mobilenet_v3_small_seg" Export Model Generate Freeze Graph (.pb) with INPUT Placeholder changed from checkpoint file (.ckpt). ```bash $ python3 deeplab/export_model.py \ --checkpoint_path=./deeplab_mnv3_small_cityscapes_trainfine/model.ckpt \ --export_path=./deeplab_mnv3_small_cityscapes_trainfine/frozen_inference_graph.pb \ --num_classes=19 \ --crop_size=769 \ --crop_size=769 \ --model_variant="mobilenet_v3_small_seg" \ --image_pooling_crop_size="769,769" \ --image_pooling_stride=4,5 \ --aspp_convs_filters=128 \ --aspp_with_concat_projection=0 \ --aspp_with_squeeze_and_excitation=1 \ --decoder_use_sum_merge=1 \ --decoder_filters=19 \ --decoder_output_is_logits=1 \ --image_se_uses_qsigmoid=1 \ --image_pyramid=1 \ --decoder_output_stride=8 ``` #### 2-2-4. "mobilenet_v3_large_seg" Export Model Generate Freeze Graph (.pb) with INPUT Placeholder changed from checkpoint file (.ckpt). ```bash $ python3 deeplab/export_model.py \ --checkpoint_path=./deeplab_mnv3_large_cityscapes_trainfine/model.ckpt \ --export_path=./deeplab_mnv3_large_cityscapes_trainfine/frozen_inference_graph.pb \ --num_classes=19 \ --crop_size=769 \ --crop_size=769 \ --model_variant="mobilenet_v3_large_seg" \ --image_pooling_crop_size="769,769" \ --image_pooling_stride=4,5 \ --aspp_convs_filters=128 \ --aspp_with_concat_projection=0 \ --aspp_with_squeeze_and_excitation=1 \ --decoder_use_sum_merge=1 \ --decoder_filters=19 \ --decoder_output_is_logits=1 \ --image_se_uses_qsigmoid=1 \ --image_pyramid=1 \ --decoder_output_stride=8 ``` If you follow the Google Colaboratory sample procedure, copy the "deeplab_mnv3_small_cityscapes_trainfine" folder and "deeplab_mnv3_large_cityscapes_trainfine" to your Google Drive "My Drive". It is not necessary if all procedures described in Google Colaboratory are performed in a PC environment.   #### 2-2-5. Google Colaboratory - Post-training quantization - post_training_integer_quant.ipynb - Weight Quantization - Integer Quantization - Full Integer Quantization https://colab.research.google.com/drive/1TtCJ-uMNTArpZxrf5DCNbZdn08DsiW8F 　 　 ### 2-3. MobileNetV3+DeeplabV3+Cityscaps - Quantization-aware training #### 2-3-1. "mobilenet_v3_small_seg" Quantization-aware training ```bash $ cd ${HOME}/git/deeplab/models/research $ export PATH_TO_TRAINED_FLOAT_MODEL=${HOME}/git/deeplab/models/research/deeplab_mnv3_small_cityscapes_trainfine/model.ckpt $ export PATH_TO_TRAIN_DIR=${HOME}/git/deeplab/models/research/deeplab/datasets/cityscapes/exp/train_on_train_set/train $ export PATH_TO_DATASET=${HOME}/git/deeplab/models/research/deeplab/datasets/cityscapes/tfrecord # deeplab_mnv3_small_cityscapes_trainfine $ python3 deeplab/train.py \ --logtostderr \ --training_number_of_steps=5000 \ --train_split="train" \ --model_variant="mobilenet_v3_small_seg" \ --train_crop_size="769,769" \ --train_batch_size=8 \ --dataset="cityscapes" \ --initialize_last_layer=False \ --base_learning_rate=3e-5 \ --quantize_delay_step=0 \ --image_pooling_crop_size="769,769" \ --image_pooling_stride=4,5 \ --aspp_convs_filters=128 \ --aspp_with_concat_projection=0 \ --aspp_with_squeeze_and_excitation=1 \ --decoder_use_sum_merge=1 \ --decoder_filters=19 \ --decoder_output_is_logits=1 \ --image_se_uses_qsigmoid=1 \ --image_pyramid=1 \ --decoder_output_stride=8 \ --save_interval_secs=300 \ --save_summaries_secs=300 \ --save_summaries_images=True \ --log_steps=100 \ --tf_initial_checkpoint=${PATH_TO_TRAINED_FLOAT_MODEL} \ --train_logdir=${PATH_TO_TRAIN_DIR} \ --dataset_dir=${PATH_TO_DATASET} ``` #### 2-3-2. "mobilenet_v3_large_seg" Quantization-aware training ```bash $ cd ${HOME}/git/deeplab/models/research $ export PATH_TO_TRAINED_FLOAT_MODEL=${HOME}/git/deeplab/models/research/deeplab_mnv3_large_cityscapes_trainfine/model.ckpt $ export PATH_TO_TRAIN_DIR=${HOME}/git/deeplab/models/research/deeplab/datasets/cityscapes/exp/train_on_train_set/train $ export PATH_TO_DATASET=${HOME}/git/deeplab/models/research/deeplab/datasets/cityscapes/tfrecord # deeplab_mnv3_large_cityscapes_trainfine $ python3 deeplab/train.py \ --logtostderr \ --training_number_of_steps=4350 \ --train_split="train" \ --model_variant="mobilenet_v3_large_seg" \ --train_crop_size="769,769" \ --train_batch_size=8 \ --dataset="cityscapes" \ --initialize_last_layer=False \ --base_learning_rate=3e-5 \ --quantize_delay_step=0 \ --image_pooling_crop_size="769,769" \ --image_pooling_stride=4,5 \ --aspp_convs_filters=128 \ --aspp_with_concat_projection=0 \ --aspp_with_squeeze_and_excitation=1 \ --decoder_use_sum_merge=1 \ --decoder_filters=19 \ --decoder_output_is_logits=1 \ --image_se_uses_qsigmoid=1 \ --image_pyramid=1 \ --decoder_output_stride=8 \ --save_interval_secs=300 \ --save_summaries_secs=300 \ --save_summaries_images=True \ --log_steps=100 \ --tf_initial_checkpoint=${PATH_TO_TRAINED_FLOAT_MODEL} \ --train_logdir=${PATH_TO_TRAIN_DIR} \ --dataset_dir=${PATH_TO_DATASET} ``` The orange line is "deeplab_mnv3_small_cityscapes_trainfine" loss. The blue line is "deeplab_mnv3_large_cityscapes_trainfine" loss.  　 　 ### 2-4. MobileNetV2+DeeplabV3+coco/voc - Post-training quantization #### 2-4-1. Preparation ```bash $ cd ${HOME}/git/deeplab/models/research $ wget http://download.tensorflow.org/models/deeplabv3_mnv2_dm05_pascal_trainaug_2018_10_01.tar.gz $ tar -zxvf deeplabv3_mnv2_dm05_pascal_trainaug_2018_10_01.tar.gz $ rm deeplabv3_mnv2_dm05_pascal_trainaug_2018_10_01.tar.gz $ wget http://download.tensorflow.org/models/deeplabv3_mnv2_dm05_pascal_trainval_2018_10_01.tar.gz $ tar -zxvf deeplabv3_mnv2_dm05_pascal_trainval_2018_10_01.tar.gz $ rm deeplabv3_mnv2_dm05_pascal_trainval_2018_10_01.tar.gz $ wget http://download.tensorflow.org/models/deeplabv3_mnv2_pascal_train_aug_2018_01_29.tar.gz $ tar -zxvf deeplabv3_mnv2_pascal_train_aug_2018_01_29.tar.gz $ rm deeplabv3_mnv2_pascal_train_aug_2018_01_29.tar.gz $ sed -i -e \ "s/tf.placeholder(tf.uint8, \[1, None, None, 3\], name=_INPUT_NAME)/tf.placeholder(tf.float32, \[1, 257, 257, 3\], name=_INPUT_NAME)/g" \ deeplab/export_model.py $ export PYTHONPATH=${HOME}/git/deeplab/models/research:${HOME}/git/deeplab/models/research/deeplab:${HOME}/git/deeplab/models/research/slim:${PYTHONPATH} $ python3 deeplab/export_model.py \ --checkpoint_path=./deeplabv3_mnv2_dm05_pascal_trainaug/model.ckpt \ --export_path=./deeplabv3_mnv2_dm05_pascal_trainaug/frozen_inference_graph.pb \ --model_variant="mobilenet_v2" \ --crop_size=257 \ --crop_size=257 \ --depth_multiplier=0.5 $ python3 deeplab/export_model.py \ --checkpoint_path=./deeplabv3_mnv2_dm05_pascal_trainval/model.ckpt \ --export_path=./deeplabv3_mnv2_dm05_pascal_trainval/frozen_inference_graph.pb \ --model_variant="mobilenet_v2" \ --crop_size=257 \ --crop_size=257 \ --depth_multiplier=0.5 $ python3 deeplab/export_model.py \ --checkpoint_path=./deeplabv3_mnv2_pascal_train_aug/model.ckpt-30000 \ --export_path=./deeplabv3_mnv2_pascal_train_aug/frozen_inference_graph.pb \ --model_variant="mobilenet_v2" \ --crop_size=257 \ --crop_size=257 ``` ### 2-5. MobileNetV3-SSD+coco - Post-training quantization #### 2-5-1. Preparation ```bash $ cd ~ $ sudo pip3 install tensorflow-gpu==1.15.0 $ git clone --depth 1 https://github.com/tensorflow/models.git $ cd models/research $ git clone https://github.com/cocodataset/cocoapi.git $ cd cocoapi/PythonAPI $ make $ cp -r pycocotools ../.. $ cd ../.. $ wget -O protobuf.zip https://github.com/google/protobuf/releases/download/v3.0.0/protoc-3.0.0-linux-x86_64.zip $ unzip protobuf.zip $ ./bin/protoc object_detection/protos/*.proto --python_out=. $ sudo apt-get install -y protobuf-compiler python3-pil python3-lxml python3-tk $ sudo -H pip3 install Cython contextlib2 jupyter matplotlib $ export PYTHONPATH=${PWD}:${PWD}/object_detection:${PWD}/slim:${PYTHONPATH} $ mkdir -p ssd_mobilenet_v3_small_coco_2019_08_14 && cd ssd_mobilenet_v3_small_coco_2019_08_14 $ curl -sc /tmp/cookie "https://drive.google.com/uc?export=download&id=1uqaC0Y-yRtzkpu1EuZ3BzOyh9-i_3Qgi" > /dev/null $ CODE="$(awk '/_warning_/ {print $NF}' /tmp/cookie)" $ curl -Lb /tmp/cookie "https://drive.google.com/uc?export=download&confirm=${CODE}&id=1uqaC0Y-yRtzkpu1EuZ3BzOyh9-i_3Qgi" -o ssd_mobilenet_v3_small_coco_2019_08_14.tar.gz $ tar -zxvf ssd_mobilenet_v3_small_coco_2019_08_14.tar.gz $ rm ssd_mobilenet_v3_small_coco_2019_08_14.tar.gz $ cd .. $ mkdir -p ssd_mobilenet_v3_large_coco_2019_08_14 && cd ssd_mobilenet_v3_large_coco_2019_08_14 $ curl -sc /tmp/cookie "https://drive.google.com/uc?export=download&id=1NGLjKRWDQZ_kibQHlLZ7Eetuuz1waC7X" > /dev/null $ CODE="$(awk '/_warning_/ {print $NF}' /tmp/cookie)" $ curl -Lb /tmp/cookie "https://drive.google.com/uc?export=download&confirm=${CODE}&id=1NGLjKRWDQZ_kibQHlLZ7Eetuuz1waC7X" -o ssd_mobilenet_v3_large_coco_2019_08_14.tar.gz $ tar -zxvf ssd_mobilenet_v3_large_coco_2019_08_14.tar.gz $ rm ssd_mobilenet_v3_large_coco_2019_08_14.tar.gz $ cd .. ``` #### 2-5-2. Create a conversion script from checkpoint format to saved_model format ```freeze_the_saved_model.py import tensorflow as tf import os import shutil from tensorflow.python.saved_model import tag_constants from tensorflow.python.tools import freeze_graph from tensorflow.python import ops from tensorflow.tools.graph_transforms import TransformGraph def freeze_model(saved_model_dir, output_node_names, output_filename): output_graph_filename = os.path.join(saved_model_dir, output_filename) initializer_nodes = '' freeze_graph.freeze_graph( input_saved_model_dir=saved_model_dir, output_graph=output_graph_filename, saved_model_tags = tag_constants.SERVING, output_node_names=output_node_names, initializer_nodes=initializer_nodes, input_graph=None, input_saver=False, input_binary=False, input_checkpoint=None, restore_op_name=None, filename_tensor_name=None, clear_devices=True, input_meta_graph=False, ) def get_graph_def_from_file(graph_filepath): tf.reset_default_graph() with ops.Graph().as_default(): with tf.gfile.GFile(graph_filepath, 'rb') as f: graph_def = tf.GraphDef() graph_def.ParseFromString(f.read()) return graph_def def optimize_graph(model_dir, graph_filename, transforms, input_name, output_names, outname='optimized_model.pb'): input_names = [input_name] # change this as per how you have saved the model graph_def = get_graph_def_from_file(os.path.join(model_dir, graph_filename)) optimized_graph_def = TransformGraph( graph_def, input_names, output_names, transforms) tf.train.write_graph(optimized_graph_def, logdir=model_dir, as_text=False, name=outname) print('Graph optimized!') def convert_graph_def_to_saved_model(export_dir, graph_filepath, input_name, outputs): graph_def = get_graph_def_from_file(graph_filepath) with tf.Session(graph=tf.Graph()) as session: tf.import_graph_def(graph_def, name='') tf.compat.v1.saved_model.simple_save( session, export_dir,# change input_image to node.name if you know the name inputs={input_name: session.graph.get_tensor_by_name('{}:0'.format(node.name)) for node in graph_def.node if node.op=='Placeholder'}, outputs={t.rstrip(":0"):session.graph.get_tensor_by_name(t) for t in outputs} ) print('Optimized graph converted to SavedModel!') tf.compat.v1.enable_eager_execution() # Look up the name of the placeholder for the input node graph_def=get_graph_def_from_file('./ssd_mobilenet_v3_small_coco_2019_08_14/frozen_inference_graph.pb') input_name_small="" for node in graph_def.node: if node.op=='Placeholder': print("##### ssd_mobilenet_v3_small_coco_2019_08_14 - Input Node Name #####", node.name) # this will be the input node input_name_small=node.name # Look up the name of the placeholder for the input node graph_def=get_graph_def_from_file('./ssd_mobilenet_v3_large_coco_2019_08_14/frozen_inference_graph.pb') input_name_large="" for node in graph_def.node: if node.op=='Placeholder': print("##### ssd_mobilenet_v3_large_coco_2019_08_14 - Input Node Name #####", node.name) # this will be the input node input_name_large=node.name # ssd_mobilenet_v3 output names output_node_names = ['raw_outputs/class_predictions','raw_outputs/box_encodings'] outputs = ['raw_outputs/class_predictions:0','raw_outputs/box_encodings:0'] # Optimizing the graph via TensorFlow library transforms = [] optimize_graph('./ssd_mobilenet_v3_small_coco_2019_08_14', 'frozen_inference_graph.pb', transforms, input_name_small, output_node_names, outname='optimized_model_small.pb') optimize_graph('./ssd_mobilenet_v3_large_coco_2019_08_14', 'frozen_inference_graph.pb', transforms, input_name_large, output_node_names, outname='optimized_model_large.pb') # convert this to a s TF Serving compatible mode - ssd_mobilenet_v3_small_coco_2019_08_14 shutil.rmtree('./ssd_mobilenet_v3_small_coco_2019_08_14/0', ignore_errors=True) convert_graph_def_to_saved_model('./ssd_mobilenet_v3_small_coco_2019_08_14/0', './ssd_mobilenet_v3_small_coco_2019_08_14/optimized_model_small.pb', input_name_small, outputs) # convert this to a s TF Serving compatible mode - ssd_mobilenet_v3_large_coco_2019_08_14 shutil.rmtree('./ssd_mobilenet_v3_large_coco_2019_08_14/0', ignore_errors=True) convert_graph_def_to_saved_model('./ssd_mobilenet_v3_large_coco_2019_08_14/0', './ssd_mobilenet_v3_large_coco_2019_08_14/optimized_model_large.pb', input_name_large, outputs) ``` #### 2-5-3. Confirm the structure of saved_model 【ssd_mobilenet_v3_small_coco_2019_08_14】 ```bash $ saved_model_cli show --dir ./ssd_mobilenet_v3_small_coco_2019_08_14/0 --all MetaGraphDef with tag-set: 'serve' contains the following SignatureDefs: signature_def['serving_default']: The given SavedModel SignatureDef contains the following input(s): inputs['normalized_input_image_tensor'] tensor_info: dtype: DT_FLOAT shape: (1, 320, 320, 3) name: normalized_input_image_tensor:0 The given SavedModel SignatureDef contains the following output(s): outputs['raw_outputs/box_encodings'] tensor_info: dtype: DT_FLOAT shape: (1, 2034, 4) name: raw_outputs/box_encodings:0 outputs['raw_outputs/class_predictions'] tensor_info: dtype: DT_FLOAT shape: (1, 2034, 91) name: raw_outputs/class_predictions:0 Method name is: tensorflow/serving/predict ``` #### 2-5-4. Confirm the structure of saved_model 【ssd_mobilenet_v3_large_coco_2019_08_14】 ```bash $ saved_model_cli show --dir ./ssd_mobilenet_v3_large_coco_2019_08_14/0 --all MetaGraphDef with tag-set: 'serve' contains the following SignatureDefs: signature_def['serving_default']: The given SavedModel SignatureDef contains the following input(s): inputs['normalized_input_image_tensor'] tensor_info: dtype: DT_FLOAT shape: (1, 320, 320, 3) name: normalized_input_image_tensor:0 The given SavedModel SignatureDef contains the following output(s): outputs['raw_outputs/box_encodings'] tensor_info: dtype: DT_FLOAT shape: (1, 2034, 4) name: raw_outputs/box_encodings:0 outputs['raw_outputs/class_predictions'] tensor_info: dtype: DT_FLOAT shape: (1, 2034, 91) name: raw_outputs/class_predictions:0 Method name is: tensorflow/serving/predict ``` #### 2-5-5. Creating the destination path for the calibration test dataset 6GB ```bash $ curl -sc /tmp/cookie "https://drive.google.com/uc?export=download&id=1Uk9F4Tc-9UgnvARIVkloSoePUynyST6E" > /dev/null $ CODE="$(awk '/_warning_/ {print $NF}' /tmp/cookie)" $ curl -Lb /tmp/cookie "https://drive.google.com/uc?export=download&confirm=${CODE}&id=1Uk9F4Tc-9UgnvARIVkloSoePUynyST6E" -o TFDS.tar.gz $ tar -zxvf TFDS.tar.gz $ rm TFDS.tar.gz ``` #### 2-5-6. Quantization ##### 2-5-6-1. ssd_mobilenet_v3_small_coco_2019_08_14 ```quantization_ssd_mobilenet_v3_small_coco_2019_08_14.py import tensorflow as tf import tensorflow_datasets as tfds import numpy as np def representative_dataset_gen(): for data in raw_test_data.take(100): image = data['image'].numpy() image = tf.image.resize(image, (320, 320)) image = image[np.newaxis,:,:,:] yield [image] tf.compat.v1.enable_eager_execution() # Generating a calibration data set #raw_test_data, info = tfds.load(name="coco/2017", with_info=True, split="test", data_dir="./TFDS") raw_test_data, info = tfds.load(name="coco/2017", with_info=True, split="test", data_dir="./TFDS", download=False) print(info) # Weight Quantization - Input/Output=float32 converter = tf.lite.TFLiteConverter.from_saved_model('./ssd_mobilenet_v3_small_coco_2019_08_14/0') converter.optimizations = [tf.lite.Optimize.OPTIMIZE_FOR_SIZE] tflite_quant_model = converter.convert() with open('./ssd_mobilenet_v3_small_coco_2019_08_14/mobilenet_v3_small_weight_quant.tflite', 'wb') as w: w.write(tflite_quant_model) print("Weight Quantization complete! - mobilenet_v3_small_weight_quant.tflite") # Integer Quantization - Input/Output=float32 converter = tf.lite.TFLiteConverter.from_saved_model('./ssd_mobilenet_v3_small_coco_2019_08_14/0') converter.optimizations = [tf.lite.Optimize.DEFAULT] converter.representative_dataset = representative_dataset_gen tflite_quant_model = converter.convert() with open('./ssd_mobilenet_v3_small_coco_2019_08_14/mobilenet_v3_small_integer_quant.tflite', 'wb') as w: w.write(tflite_quant_model) print("Integer Quantization complete! - mobilenet_v3_small_integer_quant.tflite") # Full Integer Quantization - Input/Output=int8 converter = tf.lite.TFLiteConverter.from_saved_model('./ssd_mobilenet_v3_small_coco_2019_08_14/0') converter.optimizations = [tf.lite.Optimize.DEFAULT] converter.representative_dataset = representative_dataset_gen converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8] converter.inference_input_type = tf.uint8 converter.inference_output_type = tf.uint8 tflite_quant_model = converter.convert() with open('./ssd_mobilenet_v3_small_coco_2019_08_14/mobilenet_v3_small_full_integer_quant.tflite', 'wb') as w: w.write(tflite_quant_model) print("Full Integer Quantization complete! - mobilenet_v3_small_full_integer_quant.tflite") ``` ##### 2-5-6-2. ssd_mobilenet_v3_large_coco_2019_08_14 ```quantization_ssd_mobilenet_v3_large_coco_2019_08_14.py import tensorflow as tf import tensorflow_datasets as tfds import numpy as np def representative_dataset_gen(): for data in raw_test_data.take(100): image = data['image'].numpy() image = tf.image.resize(image, (320, 320)) image = image[np.newaxis,:,:,:] yield [image] tf.compat.v1.enable_eager_execution() # Generating a calibration data set #raw_test_data, info = tfds.load(name="coco/2017", with_info=True, split="test", data_dir="./TFDS") raw_test_data, info = tfds.load(name="coco/2017", with_info=True, split="test", data_dir="./TFDS", download=False) # Weight Quantization - Input/Output=float32 converter = tf.lite.TFLiteConverter.from_saved_model('./ssd_mobilenet_v3_large_coco_2019_08_14/0') converter.optimizations = [tf.lite.Optimize.OPTIMIZE_FOR_SIZE] tflite_quant_model = converter.convert() with open('./ssd_mobilenet_v3_large_coco_2019_08_14/mobilenet_v3_large_weight_quant.tflite', 'wb') as w: w.write(tflite_quant_model) print("Weight Quantization complete! - mobilenet_v3_large_weight_quant.tflite") # Integer Quantization - Input/Output=float32 converter = tf.lite.TFLiteConverter.from_saved_model('./ssd_mobilenet_v3_large_coco_2019_08_14/0') converter.optimizations = [tf.lite.Optimize.DEFAULT] converter.representative_dataset = representative_dataset_gen tflite_quant_model = converter.convert() with open('./ssd_mobilenet_v3_large_coco_2019_08_14/mobilenet_v3_large_integer_quant.tflite', 'wb') as w: w.write(tflite_quant_model) print("Integer Quantization complete! - mobilenet_v3_large_integer_quant.tflite") # Full Integer Quantization - Input/Output=int8 converter = tf.lite.TFLiteConverter.from_saved_model('./ssd_mobilenet_v3_large_coco_2019_08_14/0') converter.optimizations = [tf.lite.Optimize.DEFAULT] converter.representative_dataset = representative_dataset_gen converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8] converter.inference_input_type = tf.uint8 converter.inference_output_type = tf.uint8 tflite_quant_model = converter.convert() with open('./ssd_mobilenet_v3_large_coco_2019_08_14/mobilenet_v3_large_full_integer_quant.tflite', 'wb') as w: w.write(tflite_quant_model) print("Full Integer Quantization complete! - mobilenet_v3_large_full_integer_quant.tflite") ``` ### 2-6. MobileNetV2-SSDLite+VOC - Training -> Integer Quantization #### 2-6-1. Training **[Learning with the MobileNetV2-SSDLite Pascal-VOC dataset [Remake of Docker version]](https://qiita.com/PINTO/items/107dd6a4e16cb128230b)** #### 2-6-2. Export model (--add_postprocessing_op=True) **[06_mobilenetv2-ssdlite/02_voc/01_float32/00_export_tflite_model.txt](06_mobilenetv2-ssdlite/02_voc/01_float32/00_export_tflite_model.txt)** #### 2-6-3. Integer Quantization **[06_mobilenetv2-ssdlite/02_voc/01_float32/03_integer_quantization_with_postprocess.py](06_mobilenetv2-ssdlite/02_voc/01_float32/03_integer_quantization_with_postprocess.py)**

```console Number of nodes executed: 171 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 45 1251.486 67.589% 67.589% 0.000 0 DEPTHWISE_CONV_2D 11 438.764 23.696% 91.286% 0.000 0 HARD_SWISH 16 54.855 2.963% 94.248% 0.000 0 ARG_MAX 1 24.850 1.342% 95.591% 0.000 0 RESIZE_BILINEAR 5 23.805 1.286% 96.876% 0.000 0 MUL 30 14.914 0.805% 97.682% 0.000 0 ADD 18 10.646 0.575% 98.257% 0.000 0 SPACE_TO_BATCH_ND 7 9.567 0.517% 98.773% 0.000 0 BATCH_TO_SPACE_ND 7 7.431 0.401% 99.175% 0.000 0 SUB 2 6.131 0.331% 99.506% 0.000 0 AVERAGE_POOL_2D 10 5.435 0.294% 99.799% 0.000 0 RESHAPE 6 2.171 0.117% 99.916% 0.000 0 PAD 1 0.660 0.036% 99.952% 0.000 0 CAST 2 0.601 0.032% 99.985% 0.000 0 STRIDED_SLICE 1 0.277 0.015% 100.000% 0.000 0 Misc Runtime Ops 1 0.008 0.000% 100.000% 33.552 0 DEQUANTIZE 8 0.000 0.000% 100.000% 0.000 0 Timings (microseconds): count=52 first=224 curr=1869070 min=224 max=2089397 avg=1.85169e+06 std=373988 Memory (bytes): count=0 171 nodes observed ```

```console Number of nodes executed: 194 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 51 4123.348 82.616% 82.616% 0.000 0 DEPTHWISE_CONV_2D 15 628.139 12.586% 95.202% 0.000 0 HARD_SWISH 15 90.448 1.812% 97.014% 0.000 0 MUL 32 29.393 0.589% 97.603% 0.000 0 ARG_MAX 1 22.866 0.458% 98.061% 0.000 0 ADD 25 22.860 0.458% 98.519% 0.000 0 RESIZE_BILINEAR 5 22.494 0.451% 98.970% 0.000 0 SPACE_TO_BATCH_ND 8 18.518 0.371% 99.341% 0.000 0 BATCH_TO_SPACE_ND 8 15.522 0.311% 99.652% 0.000 0 AVERAGE_POOL_2D 9 7.855 0.157% 99.809% 0.000 0 SUB 2 5.896 0.118% 99.928% 0.000 0 RESHAPE 6 2.133 0.043% 99.970% 0.000 0 PAD 1 0.631 0.013% 99.983% 0.000 0 CAST 2 0.575 0.012% 99.994% 0.000 0 STRIDED_SLICE 1 0.260 0.005% 100.000% 0.000 0 Misc Runtime Ops 1 0.012 0.000% 100.000% 38.304 0 DEQUANTIZE 12 0.003 0.000% 100.000% 0.000 0 Timings (microseconds): count=31 first=193 curr=5276579 min=193 max=5454605 avg=4.99104e+06 std=1311782 Memory (bytes): count=0 194 nodes observed ```

```console Number of nodes executed: 180 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 38 37.595 45.330% 45.330% 0.000 38 ADD 37 12.319 14.854% 60.184% 0.000 37 DEPTHWISE_CONV_2D 17 11.424 13.774% 73.958% 0.000 17 RESIZE_BILINEAR 4 7.336 8.845% 82.804% 0.000 4 MUL 9 4.204 5.069% 87.873% 0.000 9 QUANTIZE 13 3.976 4.794% 92.667% 0.000 13 AVERAGE_POOL_2D 9 1.809 2.181% 94.848% 0.000 9 DIV 9 1.167 1.407% 96.255% 0.000 9 ARG_MAX 1 1.137 1.371% 97.626% 0.000 1 CONCATENATION 2 0.780 0.940% 98.566% 0.000 2 FULLY_CONNECTED 16 0.715 0.862% 99.428% 0.000 16 DEQUANTIZE 9 0.473 0.570% 99.999% 0.000 9 RESHAPE 16 0.001 0.001% 100.000% 0.000 16 Timings (microseconds): count=50 first=83065 curr=82874 min=82675 max=85743 avg=83036 std=499 Memory (bytes): count=0 180 nodes observed ```

```console Number of nodes executed: 81 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 41 47.427 65.530% 65.530% 0.000 41 DEPTHWISE_CONV_2D 19 11.114 15.356% 80.887% 0.000 19 RESIZE_BILINEAR 4 7.342 10.145% 91.031% 0.000 4 QUANTIZE 3 2.953 4.080% 95.112% 0.000 3 ADD 10 1.633 2.256% 97.368% 0.000 10 ARG_MAX 1 1.137 1.571% 98.939% 0.000 1 CONCATENATION 2 0.736 1.017% 99.956% 0.000 2 AVERAGE_POOL_2D 1 0.032 0.044% 100.000% 0.000 1 Timings (microseconds): count=50 first=72544 curr=72425 min=72157 max=72745 avg=72412.9 std=137 Memory (bytes): count=0 81 nodes observed ```

```console Number of nodes executed: 176 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 61 10.255 36.582% 36.582% 0.000 61 DEPTHWISE_CONV_2D 27 5.058 18.043% 54.625% 0.000 27 MUL 26 5.056 18.036% 72.661% 0.000 26 ADD 14 4.424 15.781% 88.442% 0.000 14 QUANTIZE 13 1.633 5.825% 94.267% 0.000 13 HARD_SWISH 10 0.918 3.275% 97.542% 0.000 10 LOGISTIC 1 0.376 1.341% 98.883% 0.000 1 AVERAGE_POOL_2D 9 0.199 0.710% 99.593% 0.000 9 CONCATENATION 2 0.084 0.300% 99.893% 0.000 2 RESHAPE 13 0.030 0.107% 100.000% 0.000 13 Timings (microseconds): count=50 first=28827 curr=28176 min=27916 max=28827 avg=28121.2 std=165 Memory (bytes): count=0 176 nodes observed ```

```console Number of nodes executed: 186 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 61 82.600 79.265% 79.265% 0.000 61 DEPTHWISE_CONV_2D 27 8.198 7.867% 87.132% 0.000 27 MUL 26 4.866 4.670% 91.802% 0.000 26 ADD 14 4.863 4.667% 96.469% 0.000 14 LOGISTIC 1 1.645 1.579% 98.047% 0.000 1 AVERAGE_POOL_2D 9 0.761 0.730% 98.777% 0.000 9 HARD_SWISH 10 0.683 0.655% 99.433% 0.000 10 CONCATENATION 2 0.415 0.398% 99.831% 0.000 2 RESHAPE 13 0.171 0.164% 99.995% 0.000 13 DEQUANTIZE 23 0.005 0.005% 100.000% 0.000 23 Timings (microseconds): count=50 first=103867 curr=103937 min=103708 max=118926 avg=104299 std=2254 Memory (bytes): count=0 186 nodes observed ```

```console Number of nodes executed: 38 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 18 31.906 83.360% 83.360% 0.000 0 DEPTHWISE_CONV_2D 13 5.959 15.569% 98.929% 0.000 0 QUANTIZE 1 0.223 0.583% 99.511% 0.000 0 Misc Runtime Ops 1 0.148 0.387% 99.898% 96.368 0 DEQUANTIZE 4 0.030 0.078% 99.976% 0.000 0 LOGISTIC 1 0.009 0.024% 100.000% 0.000 0 Timings (microseconds): count=70 first=519 curr=53370 min=519 max=53909 avg=38296 std=23892 Memory (bytes): count=0 38 nodes observed ```

```bash Number of nodes executed: 128 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 55 27.253 71.185% 71.185% 0.000 0 DEPTHWISE_CONV_2D 33 8.024 20.959% 92.143% 0.000 0 ADD 10 1.565 4.088% 96.231% 0.000 0 QUANTIZE 11 0.546 1.426% 97.657% 0.000 0 Misc Runtime Ops 1 0.368 0.961% 98.618% 250.288 0 LOGISTIC 1 0.253 0.661% 99.279% 0.000 0 DEQUANTIZE 2 0.168 0.439% 99.718% 0.000 0 CONCATENATION 2 0.077 0.201% 99.919% 0.000 0 RESHAPE 13 0.031 0.081% 100.000% 0.000 0 Timings (microseconds): count=70 first=1289 curr=53049 min=1289 max=53590 avg=38345.2 std=23436 Memory (bytes): count=0 128 nodes observed ```

```bash Number of nodes executed: 111 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] MINIMUM 35 10.020 45.282% 45.282% 0.000 35 CONV_2D 34 8.376 37.852% 83.134% 0.000 34 DEPTHWISE_CONV_2D 18 1.685 7.615% 90.749% 0.000 18 MEAN 1 1.422 6.426% 97.176% 0.000 1 FULLY_CONNECTED 2 0.589 2.662% 99.837% 0.000 2 ADD 10 0.031 0.140% 99.977% 0.000 10 SOFTMAX 1 0.005 0.023% 100.000% 0.000 1 DEQUANTIZE 10 0.000 0.000% 100.000% 0.000 10 Timings (microseconds): count=50 first=22417 curr=22188 min=22041 max=22417 avg=22182 std=70 Memory (bytes): count=0 111 nodes observed ```

```bash Number of nodes executed: 173 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] QUANTIZE 70 1.117 23.281% 23.281% 0.000 0 MINIMUM 35 1.104 23.010% 46.290% 0.000 0 CONV_2D 34 0.866 18.049% 64.339% 0.000 0 MEAN 1 0.662 13.797% 78.137% 0.000 0 DEPTHWISE_CONV_2D 18 0.476 9.921% 88.058% 0.000 0 FULLY_CONNECTED 2 0.251 5.231% 93.289% 0.000 0 Misc Runtime Ops 1 0.250 5.211% 98.499% 71.600 0 ADD 10 0.071 1.480% 99.979% 0.000 0 SOFTMAX 1 0.001 0.021% 100.000% 0.000 0 DEQUANTIZE 1 0.000 0.000% 100.000% 0.000 0 Timings (microseconds): count=198 first=477 curr=9759 min=477 max=10847 avg=4876.6 std=4629 Memory (bytes): count=0 173 nodes observed ```

```bash Number of nodes executed: 82 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 38 103.576 56.077% 56.077% 0.000 38 DEPTHWISE_CONV_2D 17 33.151 17.948% 74.026% 0.000 17 RESIZE_BILINEAR 3 15.143 8.199% 82.224% 0.000 3 SUB 2 10.908 5.906% 88.130% 0.000 2 ADD 11 9.821 5.317% 93.447% 0.000 11 ARG_MAX 1 8.824 4.777% 98.225% 0.000 1 PAD 1 1.024 0.554% 98.779% 0.000 1 QUANTIZE 2 0.941 0.509% 99.289% 0.000 2 MUL 1 0.542 0.293% 99.582% 0.000 1 CONCATENATION 1 0.365 0.198% 99.780% 0.000 1 AVERAGE_POOL_2D 1 0.150 0.081% 99.861% 0.000 1 RESHAPE 2 0.129 0.070% 99.931% 0.000 2 EXPAND_DIMS 2 0.128 0.069% 100.000% 0.000 2 Timings (microseconds): count=50 first=201226 curr=176476 min=176476 max=201226 avg=184741 std=4791 Memory (bytes): count=0 82 nodes observed ```

```bash Number of nodes executed: 8 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] DELEGATE 3 6.716 61.328% 61.328% 0.000 3 RESIZE_BILINEAR 3 3.965 36.207% 97.534% 0.000 3 CONCATENATION 1 0.184 1.680% 99.215% 0.000 1 AVERAGE_POOL_2D 1 0.086 0.785% 100.000% 0.000 1 Timings (microseconds): count=91 first=11051 curr=10745 min=10521 max=12552 avg=10955.4 std=352 Memory (bytes): count=0 8 nodes observed Note: as the benchmark tool itself affects memory footprint, the following is only APPROXIMATE to the actual memory footprint of the model at runtime. Take the information at your discretion. Peak memory footprint (MB): init=3.58203 overall=56.0703 ```

```bash Number of nodes executed: 70 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] DEPTHWISE_CONV_2D 17 41.704 68.372% 68.372% 0.000 17 CONV_2D 38 15.932 26.120% 94.491% 0.000 38 RESIZE_BILINEAR 3 3.060 5.017% 99.508% 0.000 3 ADD 10 0.149 0.244% 99.752% 0.000 10 CONCATENATION 1 0.109 0.179% 99.931% 0.000 1 AVERAGE_POOL_2D 1 0.042 0.069% 100.000% 0.000 1 Timings (microseconds): count=50 first=59929 curr=60534 min=59374 max=63695 avg=61031.6 std=1182 Memory (bytes): count=0 70 nodes observed Note: as the benchmark tool itself affects memory footprint, the following is only APPROXIMATE to the actual memory footprint of the model at runtime. Take the information at your discretion. Peak memory footprint (MB): init=0 overall=13.7109 ```

```bash umber of nodes executed: 74 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 31 4.947 77.588% 77.588% 0.000 31 DELEGATE 17 0.689 10.806% 88.394% 0.000 17 DEPTHWISE_CONV_2D 10 0.591 9.269% 97.663% 0.000 10 MEAN 1 0.110 1.725% 99.388% 0.000 1 PAD 5 0.039 0.612% 100.000% 0.000 5 DEQUANTIZE 10 0.000 0.000% 100.000% 0.000 10 Timings (microseconds): count=155 first=6415 curr=6443 min=6105 max=6863 avg=6409.22 std=69 Memory (bytes): count=0 74 nodes observed ```

```bash Number of nodes executed: 72 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 35 0.753 34.958% 34.958% 0.000 0 PAD 5 0.395 18.338% 53.296% 0.000 0 MEAN 1 0.392 18.199% 71.495% 0.000 0 Misc Runtime Ops 1 0.282 13.092% 84.587% 89.232 0 DEPTHWISE_CONV_2D 17 0.251 11.653% 96.240% 0.000 0 ADD 10 0.054 2.507% 98.747% 0.000 0 QUANTIZE 1 0.024 1.114% 99.861% 0.000 0 DEQUANTIZE 2 0.003 0.139% 100.000% 0.000 0 Timings (microseconds): count=472 first=564 curr=3809 min=564 max=3950 avg=2188.51 std=1625 Memory (bytes): count=0 72 nodes observed ```

```bash Number of nodes executed: 5 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] DELEGATE 2 5.639 95.706% 95.706% 0.000 2 FULLY_CONNECTED 1 0.239 4.056% 99.762% 0.000 1 AVERAGE_POOL_2D 1 0.014 0.238% 100.000% 0.000 1 RESHAPE 1 0.000 0.000% 100.000% 0.000 1 Timings (microseconds): count=168 first=5842 curr=5910 min=5749 max=6317 avg=5894.55 std=100 Memory (bytes): count=0 5 nodes observed ```

```bash Number of nodes executed: 5 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] DELEGATE 2 33.720 99.235% 99.235% 0.000 2 FULLY_CONNECTED 1 0.231 0.680% 99.915% 0.000 1 AVERAGE_POOL_2D 1 0.029 0.085% 100.000% 0.000 1 RESHAPE 1 0.000 0.000% 100.000% 0.000 1 Timings (microseconds): count=50 first=32459 curr=34867 min=31328 max=35730 avg=33983.5 std=1426 Memory (bytes): count=0 5 nodes observed ```

```bash Number of nodes executed: 47 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 18 10731.842 97.293% 97.293% 0.000 18 LEAKY_RELU 13 236.792 2.147% 99.440% 0.000 13 TfLiteXNNPackDelegate 10 45.534 0.413% 99.853% 0.000 10 RESIZE_BILINEAR 2 11.237 0.102% 99.954% 0.000 2 SUB 3 4.053 0.037% 99.991% 0.000 3 DIV 1 0.977 0.009% 100.000% 0.000 1 Timings (microseconds): count=14 first=10866837 curr=11292015 min=10697744 max=12289882 avg=1.10305e+07 std=406791 Memory (bytes): count=0 47 nodes observed ```

```bash Number of nodes executed: 91 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 49 54.679 58.810% 58.810% 0.000 49 SUB 2 11.043 11.877% 70.687% 0.000 2 ADD 16 8.909 9.582% 80.269% 0.000 16 ARG_MAX 1 7.184 7.727% 87.996% 0.000 1 RESIZE_BILINEAR 3 6.654 7.157% 95.153% 0.000 3 DEPTHWISE_CONV_2D 13 3.409 3.667% 98.819% 0.000 13 MUL 1 0.548 0.589% 99.408% 0.000 1 QUANTIZE 2 0.328 0.353% 99.761% 0.000 2 RESHAPE 2 0.162 0.174% 99.935% 0.000 2 AVERAGE_POOL_2D 1 0.043 0.046% 99.982% 0.000 1 CONCATENATION 1 0.017 0.018% 100.000% 0.000 1 Timings (microseconds): count=50 first=92752 curr=93058 min=92533 max=94478 avg=93021.2 std=274 Memory (bytes): count=0 91 nodes observed ```

```bash Number of nodes executed: 91 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 49 39.890 52.335% 52.335% 0.000 49 SUB 2 11.043 14.488% 66.823% 0.000 2 ADD 16 8.064 10.580% 77.403% 0.000 16 ARG_MAX 1 7.011 9.198% 86.601% 0.000 1 RESIZE_BILINEAR 3 6.623 8.689% 95.290% 0.000 3 DEPTHWISE_CONV_2D 13 2.503 3.284% 98.574% 0.000 13 MUL 1 0.544 0.714% 99.288% 0.000 1 QUANTIZE 2 0.313 0.411% 99.698% 0.000 2 RESHAPE 2 0.178 0.234% 99.932% 0.000 2 AVERAGE_POOL_2D 1 0.041 0.054% 99.986% 0.000 1 CONCATENATION 1 0.011 0.014% 100.000% 0.000 1 Timings (microseconds): count=50 first=75517 curr=75558 min=75517 max=97776 avg=76262.5 std=3087 Memory (bytes): count=0 91 nodes observed ```

```bash Number of nodes executed: 165 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 69 343.433 78.638% 78.638% 0.000 69 PAD 38 51.637 11.824% 90.462% 0.000 38 DEPTHWISE_CONV_2D 14 15.306 3.505% 93.967% 0.000 14 ADD 15 14.535 3.328% 97.295% 0.000 15 ELU 6 5.071 1.161% 98.456% 0.000 6 QUANTIZE 11 4.481 1.026% 99.482% 0.000 11 DEQUANTIZE 9 1.851 0.424% 99.906% 0.000 9 CONCATENATION 3 0.410 0.094% 100.000% 0.000 3 Timings (microseconds): count=50 first=425038 curr=423469 min=421348 max=969226 avg=436808 std=77255 Memory (bytes): count=0 165 nodes observed ```

```bash Number of nodes executed: 79 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] ADD 16 2.155 34.120% 34.120% 0.000 16 CONV_2D 21 2.017 31.935% 66.054% 0.000 21 PAD 11 1.014 16.054% 82.109% 0.000 11 DEPTHWISE_CONV_2D 16 0.765 12.112% 94.221% 0.000 16 QUANTIZE 4 0.186 2.945% 97.166% 0.000 4 MAX_POOL_2D 3 0.153 2.422% 99.588% 0.000 3 DEQUANTIZE 2 0.017 0.269% 99.857% 0.000 2 CONCATENATION 2 0.006 0.095% 99.952% 0.000 2 RESHAPE 4 0.003 0.047% 100.000% 0.000 4 Timings (microseconds): count=144 first=6415 curr=6319 min=6245 max=6826 avg=6359.12 std=69 Memory (bytes): count=0 79 nodes observed ```

```bash Number of nodes executed: 588 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 119 109.253 52.671% 52.671% 0.000 119 DEPTHWISE_CONV_2D 61 33.838 16.313% 68.984% 0.000 61 TFLite_Detection_PostProcess 1 22.711 10.949% 79.933% 0.000 1 LOGISTIC 1 17.696 8.531% 88.465% 0.000 1 ADD 59 12.300 5.930% 94.395% 0.000 59 RESHAPE 8 4.175 2.013% 96.407% 0.000 8 CONCATENATION 2 3.416 1.647% 98.054% 0.000 2 RESIZE_NEAREST_NEIGHBOR 12 1.873 0.903% 98.957% 0.000 12 MAX_POOL_2D 13 1.363 0.657% 99.614% 0.000 13 MUL 16 0.737 0.355% 99.970% 0.000 16 DEQUANTIZE 296 0.063 0.030% 100.000% 0.000 296 Timings (microseconds): count=50 first=346007 curr=196005 min=192539 max=715157 avg=207709 std=75605 Memory (bytes): count=0 588 nodes observed ```

```bash Number of nodes executed: 126 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 60 146.537 63.805% 63.805% 0.000 60 DEPTHWISE_CONV_2D 26 45.022 19.604% 83.409% 0.000 26 ADD 23 23.393 10.186% 93.595% 0.000 23 TRANSPOSE_CONV 3 9.930 4.324% 97.918% 0.000 3 QUANTIZE 5 3.103 1.351% 99.269% 0.000 5 CONCATENATION 4 1.541 0.671% 99.940% 0.000 4 DEQUANTIZE 3 0.117 0.051% 99.991% 0.000 3 EXP 1 0.018 0.008% 99.999% 0.000 1 NEG 1 0.002 0.001% 100.000% 0.000 1 Timings (microseconds): count=50 first=218224 curr=217773 min=217174 max=649357 avg=229732 std=62952 Memory (bytes): count=0 126 nodes observed ```

```bash Number of nodes executed: 288 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 96 22.996 33.342% 33.342% 0.000 96 HARD_SWISH 57 11.452 16.604% 49.946% 0.000 57 MUL 19 9.423 13.662% 63.608% 0.000 19 AVERAGE_POOL_2D 19 8.439 12.236% 75.843% 0.000 19 DEPTHWISE_CONV_2D 35 7.810 11.324% 87.167% 0.000 35 TFLite_Detection_PostProcess 1 5.650 8.192% 95.359% 0.000 1 ADD 12 1.690 2.450% 97.809% 0.000 12 QUANTIZE 12 0.879 1.274% 99.084% 0.000 12 LOGISTIC 20 0.277 0.402% 99.485% 0.000 20 DEQUANTIZE 2 0.234 0.339% 99.825% 0.000 2 CONCATENATION 2 0.079 0.115% 99.939% 0.000 2 RESHAPE 13 0.042 0.061% 100.000% 0.000 13 Timings (microseconds): count=50 first=69091 curr=68590 min=68478 max=83971 avg=69105.3 std=2147 Memory (bytes): count=0 288 nodes observed ```

```bash Number of nodes executed: 189 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 86 51.819 70.575% 70.575% 0.000 86 DEPTHWISE_CONV_2D 73 18.207 24.797% 95.372% 0.000 73 ADD 8 1.243 1.693% 97.065% 0.000 8 QUANTIZE 13 1.132 1.542% 98.607% 0.000 13 CONCATENATION 7 0.607 0.827% 99.433% 0.000 7 RESIZE_BILINEAR 1 0.354 0.482% 99.916% 0.000 1 DEQUANTIZE 1 0.062 0.084% 100.000% 0.000 1 Timings (microseconds): count=50 first=73752 curr=73430 min=73191 max=75764 avg=73524.8 std=485 Memory (bytes): count=0 189 nodes observed ```

```bash Number of nodes executed: 189 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 86 141.296 69.289% 69.289% 0.000 86 DEPTHWISE_CONV_2D 73 53.244 26.110% 95.399% 0.000 73 QUANTIZE 13 3.059 1.500% 96.899% 0.000 13 ADD 8 3.014 1.478% 98.377% 0.000 8 CONCATENATION 7 2.302 1.129% 99.506% 0.000 7 RESIZE_BILINEAR 1 0.852 0.418% 99.924% 0.000 1 DEQUANTIZE 1 0.155 0.076% 100.000% 0.000 1 Timings (microseconds): count=50 first=189613 curr=579873 min=189125 max=579873 avg=204021 std=70304 Memory (bytes): count=0 189 nodes observed ```

```bash Number of nodes executed: 189 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 86 40.952 71.786% 71.786% 0.000 86 DEPTHWISE_CONV_2D 73 13.508 23.679% 95.465% 0.000 73 QUANTIZE 13 1.123 1.969% 97.434% 0.000 13 ADD 8 0.710 1.245% 98.678% 0.000 8 CONCATENATION 7 0.498 0.873% 99.551% 0.000 7 RESIZE_BILINEAR 1 0.193 0.338% 99.890% 0.000 1 DEQUANTIZE 1 0.063 0.110% 100.000% 0.000 1 Timings (microseconds): count=50 first=57027 curr=57048 min=56773 max=58042 avg=57135 std=229 Memory (bytes): count=0 189 nodes observed ```

```bash Number of nodes executed: 189 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 86 104.618 71.523% 71.523% 0.000 86 DEPTHWISE_CONV_2D 73 34.527 23.605% 95.128% 0.000 73 QUANTIZE 13 2.572 1.758% 96.886% 0.000 13 CONCATENATION 7 2.257 1.543% 98.429% 0.000 7 ADD 8 1.683 1.151% 99.580% 0.000 8 RESIZE_BILINEAR 1 0.460 0.314% 99.894% 0.000 1 DEQUANTIZE 1 0.155 0.106% 100.000% 0.000 1 Timings (microseconds): count=50 first=172545 curr=146065 min=145260 max=172545 avg=146362 std=3756 Memory (bytes): count=0 189 nodes observed ```

```bash Number of nodes executed: 71 ============================== Summary by node type ============================== [Node type] [count] [avg ms] [avg %] [cdf %] [mem KB] [times called] CONV_2D 21 149.092 61.232% 61.232% 0.000 21 LEAKY_RELU 19 77.644 31.888% 93.121% 0.000 19 PAD 2 8.036 3.300% 96.421% 0.000 2 QUANTIZE 10 4.580 1.881% 98.302% 0.000 10 CONCATENATION 7 2.415 0.992% 99.294% 0.000 7 MAX_POOL_2D 3 0.982 0.403% 99.697% 0.000 3 SPLIT 3 0.615 0.253% 99.950% 0.000 3 DEQUANTIZE 2 0.082 0.034% 99.984% 0.000 2 RESIZE_NEAREST_NEIGHBOR 1 0.032 0.013% 99.997% 0.000 1 STRIDED_SLICE 1 0.004 0.002% 99.998% 0.000 1 MUL 1 0.004 0.002% 100.000% 0.000 1 SHAPE 1 0.000 0.000% 100.000% 0.000 1 Timings (microseconds): count=50 first=233307 curr=233318 min=232446 max=364068 avg=243522 std=33354 Memory (bytes): count=0 71 nodes observed ```