6号笔记本 tensorflow cpu object detection api

6号笔记本环境配置

done
#
# To activate this environment, use
#
#     $ conda activate wind_202103
#
# To deactivate an active environment, use
#
#     $ conda deactivate


(base) F:\>
(base) F:\>
(base) F:\>
(base) F:\>
(base) F:\>
(base) F:\>
(base) F:\>

 

测试

(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>python object_detection/builders/model_builder_tf2_test.py
2021-04-12 14:15:52.486730: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cudart64_110.dll
Running tests under Python 3.7.10: E:\Anaconda3\install\envs\wind_202103\python.exe
[ RUN      ] ModelBuilderTF2Test.test_create_center_net_model
2021-04-12 14:15:55.906964: I tensorflow/compiler/jit/xla_cpu_device.cc:41] Not creating XLA devices, tf_xla_enable_xla_devices not set
2021-04-12 14:15:55.914149: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library nvcuda.dll
2021-04-12 14:15:58.094186: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1720] Found device 0 with properties:
pciBusID: 0000:01:00.0 name: GeForce RTX 3080 Laptop GPU computeCapability: 8.6
coreClock: 1.245GHz coreCount: 48 deviceMemorySize: 16.00GiB deviceMemoryBandwidth: 357.69GiB/s
2021-04-12 14:15:58.094455: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cudart64_110.dll
2021-04-12 14:15:58.144854: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cublas64_11.dll
2021-04-12 14:15:58.144929: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cublasLt64_11.dll
2021-04-12 14:15:58.170496: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cufft64_10.dll
2021-04-12 14:15:58.178093: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library curand64_10.dll
2021-04-12 14:15:58.182160: W tensorflow/stream_executor/platform/default/dso_loader.cc:60] Could not load dynamic library 'cusolver64_10.dll'; dlerror: cusolver64_10.dll not found
2021-04-12 14:15:58.199838: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cusparse64_11.dll
2021-04-12 14:15:58.203486: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cudnn64_8.dll
2021-04-12 14:15:58.203589: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1757] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.
Skipping registering GPU devices...
2021-04-12 14:15:58.204149: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2021-04-12 14:15:58.204888: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1261] Device interconnect StreamExecutor with strength 1 edge matrix:
2021-04-12 14:15:58.207014: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1267]
2021-04-12 14:15:58.211032: I tensorflow/compiler/jit/xla_gpu_device.cc:99] Not creating XLA devices, tf_xla_enable_xla_devices not set
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_center_net_model): 2.91s
I0412 14:15:58.526351 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_center_net_model): 2.91s
[       OK ] ModelBuilderTF2Test.test_create_center_net_model
[ RUN      ] ModelBuilderTF2Test.test_create_center_net_model_from_keypoints
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_center_net_model_from_keypoints): 0.25s
I0412 14:15:58.776292 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_center_net_model_from_keypoints): 0.25s
[       OK ] ModelBuilderTF2Test.test_create_center_net_model_from_keypoints
[ RUN      ] ModelBuilderTF2Test.test_create_experimental_model
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_experimental_model): 0.0s
I0412 14:15:58.776292 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_experimental_model): 0.0s
[       OK ] ModelBuilderTF2Test.test_create_experimental_model
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature0 (True)
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature0 (True)): 0.03s
I0412 14:15:58.807536 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature0 (True)): 0.03s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature0 (True)
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature1 (False)
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature1 (False)): 0.02s
I0412 14:15:58.823157 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature1 (False)): 0.02s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature1 (False)
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_model_from_config_with_example_miner
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_model_from_config_with_example_miner): 0.02s
I0412 14:15:58.838778 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_model_from_config_with_example_miner): 0.02s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_model_from_config_with_example_miner
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul): 0.09s
I0412 14:15:58.932541 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul): 0.09s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul): 0.08s
I0412 14:15:59.027438 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul): 0.08s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul): 0.1s
I0412 14:15:59.138765 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul): 0.1s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul): 0.09s
I0412 14:15:59.232494 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul): 0.09s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul
[ RUN      ] ModelBuilderTF2Test.test_create_rfcn_model_from_config
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_rfcn_model_from_config): 0.09s
I0412 14:15:59.341844 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_rfcn_model_from_config): 0.09s
[       OK ] ModelBuilderTF2Test.test_create_rfcn_model_from_config
[ RUN      ] ModelBuilderTF2Test.test_create_ssd_fpn_model_from_config
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_ssd_fpn_model_from_config): 0.03s
I0412 14:15:59.374269 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_ssd_fpn_model_from_config): 0.03s
[       OK ] ModelBuilderTF2Test.test_create_ssd_fpn_model_from_config
[ RUN      ] ModelBuilderTF2Test.test_create_ssd_models_from_config
I0412 14:15:59.589379 11224 ssd_efficientnet_bifpn_feature_extractor.py:143] EfficientDet EfficientNet backbone version: efficientnet-b0
I0412 14:15:59.589379 11224 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet BiFPN num filters: 64
I0412 14:15:59.589379 11224 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet BiFPN num iterations: 3
I0412 14:15:59.589379 11224 efficientnet_model.py:147] round_filter input=32 output=32
I0412 14:15:59.605001 11224 efficientnet_model.py:147] round_filter input=32 output=32
I0412 14:15:59.605001 11224 efficientnet_model.py:147] round_filter input=16 output=16
I0412 14:15:59.636244 11224 efficientnet_model.py:147] round_filter input=16 output=16
I0412 14:15:59.636244 11224 efficientnet_model.py:147] round_filter input=24 output=24
I0412 14:15:59.746711 11224 efficientnet_model.py:147] round_filter input=24 output=24
I0412 14:15:59.746711 11224 efficientnet_model.py:147] round_filter input=40 output=40
I0412 14:15:59.847079 11224 efficientnet_model.py:147] round_filter input=40 output=40
I0412 14:15:59.847079 11224 efficientnet_model.py:147] round_filter input=80 output=80
I0412 14:16:00.003327 11224 efficientnet_model.py:147] round_filter input=80 output=80
I0412 14:16:00.003327 11224 efficientnet_model.py:147] round_filter input=112 output=112
I0412 14:16:00.160682 11224 efficientnet_model.py:147] round_filter input=112 output=112
I0412 14:16:00.160682 11224 efficientnet_model.py:147] round_filter input=192 output=192
I0412 14:16:00.420666 11224 efficientnet_model.py:147] round_filter input=192 output=192
I0412 14:16:00.420666 11224 efficientnet_model.py:147] round_filter input=320 output=320
I0412 14:16:00.484324 11224 efficientnet_model.py:147] round_filter input=1280 output=1280
I0412 14:16:00.515606 11224 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=1.0, depth_coefficient=1.0, resolution=224, dropout_rate=0.2, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0412 14:16:00.572247 11224 ssd_efficientnet_bifpn_feature_extractor.py:143] EfficientDet EfficientNet backbone version: efficientnet-b1
I0412 14:16:00.572247 11224 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet BiFPN num filters: 88
I0412 14:16:00.572247 11224 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet BiFPN num iterations: 4
I0412 14:16:00.572247 11224 efficientnet_model.py:147] round_filter input=32 output=32
I0412 14:16:00.587869 11224 efficientnet_model.py:147] round_filter input=32 output=32
I0412 14:16:00.587869 11224 efficientnet_model.py:147] round_filter input=16 output=16
I0412 14:16:00.665976 11224 efficientnet_model.py:147] round_filter input=16 output=16
I0412 14:16:00.665976 11224 efficientnet_model.py:147] round_filter input=24 output=24
I0412 14:16:00.822189 11224 efficientnet_model.py:147] round_filter input=24 output=24
I0412 14:16:00.822189 11224 efficientnet_model.py:147] round_filter input=40 output=40
I0412 14:16:00.981099 11224 efficientnet_model.py:147] round_filter input=40 output=40
I0412 14:16:00.981099 11224 efficientnet_model.py:147] round_filter input=80 output=80
I0412 14:16:01.184208 11224 efficientnet_model.py:147] round_filter input=80 output=80
I0412 14:16:01.184208 11224 efficientnet_model.py:147] round_filter input=112 output=112
I0412 14:16:01.391219 11224 efficientnet_model.py:147] round_filter input=112 output=112
I0412 14:16:01.391219 11224 efficientnet_model.py:147] round_filter input=192 output=192
I0412 14:16:01.672546 11224 efficientnet_model.py:147] round_filter input=192 output=192
I0412 14:16:01.672546 11224 efficientnet_model.py:147] round_filter input=320 output=320
I0412 14:16:01.801679 11224 efficientnet_model.py:147] round_filter input=1280 output=1280
I0412 14:16:01.832922 11224 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=1.0, depth_coefficient=1.1, resolution=240, dropout_rate=0.2, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0412 14:16:01.879786 11224 ssd_efficientnet_bifpn_feature_extractor.py:143] EfficientDet EfficientNet backbone version: efficientnet-b2
I0412 14:16:01.879786 11224 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet BiFPN num filters: 112
I0412 14:16:01.879786 11224 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet BiFPN num iterations: 5
I0412 14:16:01.895407 11224 efficientnet_model.py:147] round_filter input=32 output=32
I0412 14:16:01.895407 11224 efficientnet_model.py:147] round_filter input=32 output=32
I0412 14:16:01.911029 11224 efficientnet_model.py:147] round_filter input=16 output=16
I0412 14:16:01.989136 11224 efficientnet_model.py:147] round_filter input=16 output=16
I0412 14:16:01.989136 11224 efficientnet_model.py:147] round_filter input=24 output=24
I0412 14:16:02.130882 11224 efficientnet_model.py:147] round_filter input=24 output=24
I0412 14:16:02.130882 11224 efficientnet_model.py:147] round_filter input=40 output=48
I0412 14:16:02.293226 11224 efficientnet_model.py:147] round_filter input=40 output=48
I0412 14:16:02.293226 11224 efficientnet_model.py:147] round_filter input=80 output=88
I0412 14:16:02.497462 11224 efficientnet_model.py:147] round_filter input=80 output=88
I0412 14:16:02.497462 11224 efficientnet_model.py:147] round_filter input=112 output=120
I0412 14:16:02.780225 11224 efficientnet_model.py:147] round_filter input=112 output=120
I0412 14:16:02.780225 11224 efficientnet_model.py:147] round_filter input=192 output=208
I0412 14:16:03.053839 11224 efficientnet_model.py:147] round_filter input=192 output=208
I0412 14:16:03.053839 11224 efficientnet_model.py:147] round_filter input=320 output=352
I0412 14:16:03.178811 11224 efficientnet_model.py:147] round_filter input=1280 output=1408
I0412 14:16:03.210053 11224 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=1.1, depth_coefficient=1.2, resolution=260, dropout_rate=0.3, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0412 14:16:03.272538 11224 ssd_efficientnet_bifpn_feature_extractor.py:143] EfficientDet EfficientNet backbone version: efficientnet-b3
I0412 14:16:03.272538 11224 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet BiFPN num filters: 160
I0412 14:16:03.272538 11224 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet BiFPN num iterations: 6
I0412 14:16:03.288159 11224 efficientnet_model.py:147] round_filter input=32 output=40
I0412 14:16:03.288159 11224 efficientnet_model.py:147] round_filter input=32 output=40
I0412 14:16:03.288159 11224 efficientnet_model.py:147] round_filter input=16 output=24
I0412 14:16:03.367403 11224 efficientnet_model.py:147] round_filter input=16 output=24
I0412 14:16:03.367403 11224 efficientnet_model.py:147] round_filter input=24 output=32
I0412 14:16:03.525760 11224 efficientnet_model.py:147] round_filter input=24 output=32
I0412 14:16:03.525760 11224 efficientnet_model.py:147] round_filter input=40 output=48
I0412 14:16:03.681978 11224 efficientnet_model.py:147] round_filter input=40 output=48
I0412 14:16:03.681978 11224 efficientnet_model.py:147] round_filter input=80 output=96
I0412 14:16:03.936995 11224 efficientnet_model.py:147] round_filter input=80 output=96
I0412 14:16:03.936995 11224 efficientnet_model.py:147] round_filter input=112 output=136
I0412 14:16:04.211657 11224 efficientnet_model.py:147] round_filter input=112 output=136
I0412 14:16:04.211657 11224 efficientnet_model.py:147] round_filter input=192 output=232
I0412 14:16:04.560706 11224 efficientnet_model.py:147] round_filter input=192 output=232
I0412 14:16:04.560706 11224 efficientnet_model.py:147] round_filter input=320 output=384
I0412 14:16:04.701331 11224 efficientnet_model.py:147] round_filter input=1280 output=1536
I0412 14:16:04.732574 11224 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=1.2, depth_coefficient=1.4, resolution=300, dropout_rate=0.3, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0412 14:16:04.795061 11224 ssd_efficientnet_bifpn_feature_extractor.py:143] EfficientDet EfficientNet backbone version: efficientnet-b4
I0412 14:16:04.795061 11224 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet BiFPN num filters: 224
I0412 14:16:04.795061 11224 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet BiFPN num iterations: 7
I0412 14:16:04.795061 11224 efficientnet_model.py:147] round_filter input=32 output=48
I0412 14:16:04.810693 11224 efficientnet_model.py:147] round_filter input=32 output=48
I0412 14:16:04.810693 11224 efficientnet_model.py:147] round_filter input=16 output=24
I0412 14:16:04.889998 11224 efficientnet_model.py:147] round_filter input=16 output=24
I0412 14:16:04.889998 11224 efficientnet_model.py:147] round_filter input=24 output=32
I0412 14:16:05.079239 11224 efficientnet_model.py:147] round_filter input=24 output=32
I0412 14:16:05.079239 11224 efficientnet_model.py:147] round_filter input=40 output=56
I0412 14:16:05.410891 11224 efficientnet_model.py:147] round_filter input=40 output=56
I0412 14:16:05.410891 11224 efficientnet_model.py:147] round_filter input=80 output=112
I0412 14:16:05.725448 11224 efficientnet_model.py:147] round_filter input=80 output=112
I0412 14:16:05.725448 11224 efficientnet_model.py:147] round_filter input=112 output=160
I0412 14:16:06.054715 11224 efficientnet_model.py:147] round_filter input=112 output=160
I0412 14:16:06.054715 11224 efficientnet_model.py:147] round_filter input=192 output=272
I0412 14:16:06.576864 11224 efficientnet_model.py:147] round_filter input=192 output=272
I0412 14:16:06.576864 11224 efficientnet_model.py:147] round_filter input=320 output=448
I0412 14:16:06.717458 11224 efficientnet_model.py:147] round_filter input=1280 output=1792
I0412 14:16:06.749806 11224 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=1.4, depth_coefficient=1.8, resolution=380, dropout_rate=0.4, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0412 14:16:06.824114 11224 ssd_efficientnet_bifpn_feature_extractor.py:143] EfficientDet EfficientNet backbone version: efficientnet-b5
I0412 14:16:06.824114 11224 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet BiFPN num filters: 288
I0412 14:16:06.824114 11224 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet BiFPN num iterations: 7
I0412 14:16:06.824114 11224 efficientnet_model.py:147] round_filter input=32 output=48
I0412 14:16:06.839785 11224 efficientnet_model.py:147] round_filter input=32 output=48
I0412 14:16:06.839785 11224 efficientnet_model.py:147] round_filter input=16 output=24
I0412 14:16:06.964734 11224 efficientnet_model.py:147] round_filter input=16 output=24
I0412 14:16:06.964734 11224 efficientnet_model.py:147] round_filter input=24 output=40
I0412 14:16:07.215926 11224 efficientnet_model.py:147] round_filter input=24 output=40
I0412 14:16:07.215926 11224 efficientnet_model.py:147] round_filter input=40 output=64
I0412 14:16:07.462391 11224 efficientnet_model.py:147] round_filter input=40 output=64
I0412 14:16:07.462391 11224 efficientnet_model.py:147] round_filter input=80 output=128
I0412 14:16:07.847848 11224 efficientnet_model.py:147] round_filter input=80 output=128
I0412 14:16:07.847848 11224 efficientnet_model.py:147] round_filter input=112 output=176
I0412 14:16:08.227632 11224 efficientnet_model.py:147] round_filter input=112 output=176
I0412 14:16:08.227632 11224 efficientnet_model.py:147] round_filter input=192 output=304
I0412 14:16:08.935734 11224 efficientnet_model.py:147] round_filter input=192 output=304
I0412 14:16:08.935734 11224 efficientnet_model.py:147] round_filter input=320 output=512
I0412 14:16:09.201296 11224 efficientnet_model.py:147] round_filter input=1280 output=2048
I0412 14:16:09.248161 11224 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=1.6, depth_coefficient=2.2, resolution=456, dropout_rate=0.4, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0412 14:16:09.327469 11224 ssd_efficientnet_bifpn_feature_extractor.py:143] EfficientDet EfficientNet backbone version: efficientnet-b6
I0412 14:16:09.327469 11224 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet BiFPN num filters: 384
I0412 14:16:09.327469 11224 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet BiFPN num iterations: 8
I0412 14:16:09.330456 11224 efficientnet_model.py:147] round_filter input=32 output=56
I0412 14:16:09.330456 11224 efficientnet_model.py:147] round_filter input=32 output=56
I0412 14:16:09.330456 11224 efficientnet_model.py:147] round_filter input=16 output=32
I0412 14:16:09.455431 11224 efficientnet_model.py:147] round_filter input=16 output=32
I0412 14:16:09.455431 11224 efficientnet_model.py:147] round_filter input=24 output=40
I0412 14:16:09.769093 11224 efficientnet_model.py:147] round_filter input=24 output=40
I0412 14:16:09.769093 11224 efficientnet_model.py:147] round_filter input=40 output=72
I0412 14:16:10.072026 11224 efficientnet_model.py:147] round_filter input=40 output=72
I0412 14:16:10.072026 11224 efficientnet_model.py:147] round_filter input=80 output=144
I0412 14:16:10.504786 11224 efficientnet_model.py:147] round_filter input=80 output=144
I0412 14:16:10.504786 11224 efficientnet_model.py:147] round_filter input=112 output=200
I0412 14:16:10.973426 11224 efficientnet_model.py:147] round_filter input=112 output=200
I0412 14:16:10.973426 11224 efficientnet_model.py:147] round_filter input=192 output=344
I0412 14:16:11.731940 11224 efficientnet_model.py:147] round_filter input=192 output=344
I0412 14:16:11.731940 11224 efficientnet_model.py:147] round_filter input=320 output=576
I0412 14:16:12.084060 11224 efficientnet_model.py:147] round_filter input=1280 output=2304
I0412 14:16:12.130926 11224 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=1.8, depth_coefficient=2.6, resolution=528, dropout_rate=0.5, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0412 14:16:12.209056 11224 ssd_efficientnet_bifpn_feature_extractor.py:143] EfficientDet EfficientNet backbone version: efficientnet-b7
I0412 14:16:12.209056 11224 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet BiFPN num filters: 384
I0412 14:16:12.224833 11224 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet BiFPN num iterations: 8
I0412 14:16:12.224833 11224 efficientnet_model.py:147] round_filter input=32 output=64
I0412 14:16:12.224833 11224 efficientnet_model.py:147] round_filter input=32 output=64
I0412 14:16:12.224833 11224 efficientnet_model.py:147] round_filter input=16 output=32
I0412 14:16:12.388885 11224 efficientnet_model.py:147] round_filter input=16 output=32
I0412 14:16:12.388885 11224 efficientnet_model.py:147] round_filter input=24 output=48
I0412 14:16:12.748528 11224 efficientnet_model.py:147] round_filter input=24 output=48
I0412 14:16:12.748528 11224 efficientnet_model.py:147] round_filter input=40 output=80
I0412 14:16:13.119887 11224 efficientnet_model.py:147] round_filter input=40 output=80
I0412 14:16:13.119887 11224 efficientnet_model.py:147] round_filter input=80 output=160
I0412 14:16:13.672224 11224 efficientnet_model.py:147] round_filter input=80 output=160
I0412 14:16:13.672224 11224 efficientnet_model.py:147] round_filter input=112 output=224
I0412 14:16:14.254858 11224 efficientnet_model.py:147] round_filter input=112 output=224
I0412 14:16:14.254858 11224 efficientnet_model.py:147] round_filter input=192 output=384
I0412 14:16:15.250613 11224 efficientnet_model.py:147] round_filter input=192 output=384
I0412 14:16:15.250613 11224 efficientnet_model.py:147] round_filter input=320 output=640
I0412 14:16:15.611495 11224 efficientnet_model.py:147] round_filter input=1280 output=2560
I0412 14:16:15.658359 11224 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=2.0, depth_coefficient=3.1, resolution=600, dropout_rate=0.5, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_ssd_models_from_config): 16.39s
I0412 14:16:15.767739 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_ssd_models_from_config): 16.39s
[       OK ] ModelBuilderTF2Test.test_create_ssd_models_from_config
[ RUN      ] ModelBuilderTF2Test.test_invalid_faster_rcnn_batchnorm_update
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_invalid_faster_rcnn_batchnorm_update): 0.0s
I0412 14:16:15.767739 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_invalid_faster_rcnn_batchnorm_update): 0.0s
[       OK ] ModelBuilderTF2Test.test_invalid_faster_rcnn_batchnorm_update
[ RUN      ] ModelBuilderTF2Test.test_invalid_first_stage_nms_iou_threshold
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_invalid_first_stage_nms_iou_threshold): 0.0s
I0412 14:16:15.783332 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_invalid_first_stage_nms_iou_threshold): 0.0s
[       OK ] ModelBuilderTF2Test.test_invalid_first_stage_nms_iou_threshold
[ RUN      ] ModelBuilderTF2Test.test_invalid_model_config_proto
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_invalid_model_config_proto): 0.0s
I0412 14:16:15.792893 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_invalid_model_config_proto): 0.0s
[       OK ] ModelBuilderTF2Test.test_invalid_model_config_proto
[ RUN      ] ModelBuilderTF2Test.test_invalid_second_stage_batch_size
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_invalid_second_stage_batch_size): 0.0s
I0412 14:16:15.796538 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_invalid_second_stage_batch_size): 0.0s
[       OK ] ModelBuilderTF2Test.test_invalid_second_stage_batch_size
[ RUN      ] ModelBuilderTF2Test.test_session
[  SKIPPED ] ModelBuilderTF2Test.test_session
[ RUN      ] ModelBuilderTF2Test.test_unknown_faster_rcnn_feature_extractor
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_unknown_faster_rcnn_feature_extractor): 0.0s
I0412 14:16:15.801620 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_unknown_faster_rcnn_feature_extractor): 0.0s
[       OK ] ModelBuilderTF2Test.test_unknown_faster_rcnn_feature_extractor
[ RUN      ] ModelBuilderTF2Test.test_unknown_meta_architecture
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_unknown_meta_architecture): 0.0s
I0412 14:16:15.803169 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_unknown_meta_architecture): 0.0s
[       OK ] ModelBuilderTF2Test.test_unknown_meta_architecture
[ RUN      ] ModelBuilderTF2Test.test_unknown_ssd_feature_extractor
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_unknown_ssd_feature_extractor): 0.0s
I0412 14:16:15.805706 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_unknown_ssd_feature_extractor): 0.0s
[       OK ] ModelBuilderTF2Test.test_unknown_ssd_feature_extractor
----------------------------------------------------------------------
Ran 21 tests in 20.176s

OK (skipped=1)

(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>

 

 

 

 

 

安装 tensorflow-cpu

(base) F:\>
(base) F:\>
(base) F:\>
(base) F:\>
(base) F:\>
(base) F:\>conda activate wind_202103

(wind_202103) F:\>
(wind_202103) F:\>
(wind_202103) F:\>
(wind_202103) F:\>
(wind_202103) F:\>pip install tensorflow-cpu==2.2.2
Collecting tensorflow-cpu==2.2.2
  Downloading tensorflow_cpu-2.2.2-cp37-cp37m-win_amd64.whl (189.3 MB)
     |████████████████████████████████| 189.3 MB 1.1 MB/s
Collecting termcolor>=1.1.0
  Using cached termcolor-1.1.0-py3-none-any.whl
Collecting gast==0.3.3
  Using cached gast-0.3.3-py2.py3-none-any.whl (9.7 kB)
Collecting h5py<2.11.0,>=2.10.0
  Using cached h5py-2.10.0-cp37-cp37m-win_amd64.whl (2.5 MB)
Collecting opt-einsum>=2.3.2
  Using cached opt_einsum-3.3.0-py3-none-any.whl (65 kB)
Collecting absl-py>=0.7.0
  Using cached absl_py-0.12.0-py3-none-any.whl (129 kB)
Collecting tensorflow-estimator<2.3.0,>=2.2.0
  Downloading tensorflow_estimator-2.2.0-py2.py3-none-any.whl (454 kB)
     |████████████████████████████████| 454 kB 1.3 MB/s
Requirement already satisfied: wheel>=0.26 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from tensorflow-cpu==2.2.2) (0.36.2)
Collecting protobuf>=3.8.0
  Downloading protobuf-3.15.8-cp37-cp37m-win_amd64.whl (904 kB)
     |████████████████████████████████| 904 kB 1.3 MB/s
Collecting six>=1.12.0
  Using cached six-1.15.0-py2.py3-none-any.whl (10 kB)
Collecting google-pasta>=0.1.8
  Using cached google_pasta-0.2.0-py3-none-any.whl (57 kB)
Collecting numpy<1.19.0,>=1.16.0
  Downloading numpy-1.18.5-cp37-cp37m-win_amd64.whl (12.7 MB)
     |████████████████████████████████| 12.7 MB 1.3 MB/s
Collecting wrapt>=1.11.1
  Using cached wrapt-1.12.1-cp37-cp37m-win_amd64.whl
Collecting astunparse==1.6.3
  Using cached astunparse-1.6.3-py2.py3-none-any.whl (12 kB)
Collecting keras-preprocessing>=1.1.0
  Using cached Keras_Preprocessing-1.1.2-py2.py3-none-any.whl (42 kB)
Collecting grpcio>=1.8.6
  Downloading grpcio-1.37.0-cp37-cp37m-win_amd64.whl (3.1 MB)
     |████████████████████████████████| 3.1 MB 3.3 MB/s
Collecting tensorboard<2.3.0,>=2.2.0
  Downloading tensorboard-2.2.2-py3-none-any.whl (3.0 MB)
     |████████████████████████████████| 3.0 MB 2.2 MB/s
Collecting werkzeug>=0.11.15
  Using cached Werkzeug-1.0.1-py2.py3-none-any.whl (298 kB)
Collecting requests<3,>=2.21.0
  Using cached requests-2.25.1-py2.py3-none-any.whl (61 kB)
Collecting google-auth<2,>=1.6.3
  Downloading google_auth-1.28.1-py2.py3-none-any.whl (136 kB)
     |████████████████████████████████| 136 kB 6.8 MB/s
Collecting tensorboard-plugin-wit>=1.6.0
  Using cached tensorboard_plugin_wit-1.8.0-py3-none-any.whl (781 kB)
Collecting markdown>=2.6.8
  Using cached Markdown-3.3.4-py3-none-any.whl (97 kB)
Requirement already satisfied: setuptools>=41.0.0 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from tensorboard<2.3.0,>=2.2.0->tensorflow-cpu==2.2.2) (52.0.0.post20210125)
Collecting google-auth-oauthlib<0.5,>=0.4.1
  Using cached google_auth_oauthlib-0.4.4-py2.py3-none-any.whl (18 kB)
Collecting cachetools<5.0,>=2.0.0
  Using cached cachetools-4.2.1-py3-none-any.whl (12 kB)
Collecting pyasn1-modules>=0.2.1
  Using cached pyasn1_modules-0.2.8-py2.py3-none-any.whl (155 kB)
Collecting rsa<5,>=3.1.4
  Using cached rsa-4.7.2-py3-none-any.whl (34 kB)
Collecting requests-oauthlib>=0.7.0
  Using cached requests_oauthlib-1.3.0-py2.py3-none-any.whl (23 kB)
Collecting importlib-metadata
  Using cached importlib_metadata-3.10.0-py3-none-any.whl (14 kB)
Collecting pyasn1<0.5.0,>=0.4.6
  Using cached pyasn1-0.4.8-py2.py3-none-any.whl (77 kB)
Collecting chardet<5,>=3.0.2
  Using cached chardet-4.0.0-py2.py3-none-any.whl (178 kB)
Collecting idna<3,>=2.5
  Using cached idna-2.10-py2.py3-none-any.whl (58 kB)
Requirement already satisfied: certifi>=2017.4.17 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from requests<3,>=2.21.0->tensorboard<2.3.0,>=2.2.0->tensorflow-cpu==2.2.2) (2020.12.5)
Collecting urllib3<1.27,>=1.21.1
  Using cached urllib3-1.26.4-py2.py3-none-any.whl (153 kB)
Collecting oauthlib>=3.0.0
  Using cached oauthlib-3.1.0-py2.py3-none-any.whl (147 kB)
Collecting typing-extensions>=3.6.4
  Using cached typing_extensions-3.7.4.3-py3-none-any.whl (22 kB)
Collecting zipp>=0.5
  Using cached zipp-3.4.1-py3-none-any.whl (5.2 kB)
Installing collected packages: urllib3, pyasn1, idna, chardet, zipp, typing-extensions, six, rsa, requests, pyasn1-modules, oauthlib, cachetools, requests-oauthlib, importlib-metadata, google-auth, werkzeug, tensorboard-plugin-wit, protobuf, numpy, markdown, grpcio, google-auth-oauthlib, absl-py, wrapt, termcolor, tensorflow-estimator, tensorboard, opt-einsum, keras-preprocessing, h5py, google-pasta, gast, astunparse, tensorflow-cpu
Successfully installed absl-py-0.12.0 astunparse-1.6.3 cachetools-4.2.1 chardet-4.0.0 gast-0.3.3 google-auth-1.28.1 google-auth-oauthlib-0.4.4 google-pasta-0.2.0 grpcio-1.37.0 h5py-2.10.0 idna-2.10 importlib-metadata-3.10.0 keras-preprocessing-1.1.2 markdown-3.3.4 numpy-1.18.5 oauthlib-3.1.0 opt-einsum-3.3.0 protobuf-3.15.8 pyasn1-0.4.8 pyasn1-modules-0.2.8 requests-2.25.1 requests-oauthlib-1.3.0 rsa-4.7.2 six-1.15.0 tensorboard-2.2.2 tensorboard-plugin-wit-1.8.0 tensorflow-cpu-2.2.2 tensorflow-estimator-2.2.0 termcolor-1.1.0 typing-extensions-3.7.4.3 urllib3-1.26.4 werkzeug-1.0.1 wrapt-1.12.1 zipp-3.4.1

(wind_202103) F:\>
(wind_202103) F:\>
(wind_202103) F:\>
(wind_202103) F:\>
(wind_202103) F:\>
(wind_202103) F:\>
(wind_202103) F:\>

 

安装 object detection api

(wind_202103) F:\>cd F:\TensorflowProject\models-master\research

(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>protoc object_detection/protos/*.proto --python_out=.

(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>python -m pip install --use-feature=2020-resolver .
WARNING: --use-feature=2020-resolver no longer has any effect, since it is now the default dependency resolver in pip. This will become an error in pip 21.0.
Processing f:\tensorflowproject\models-master\research
Collecting avro-python3
  Downloading avro-python3-1.10.2.tar.gz (38 kB)
Collecting apache-beam
  Downloading apache_beam-2.28.0-cp37-cp37m-win_amd64.whl (3.6 MB)
     |████████████████████████████████| 3.6 MB 6.4 MB/s
Collecting pillow
  Using cached Pillow-8.2.0-cp37-cp37m-win_amd64.whl (2.2 MB)
Collecting lxml
  Downloading lxml-4.6.3-cp37-cp37m-win_amd64.whl (3.5 MB)
     |████████████████████████████████| 3.5 MB 251 kB/s
Collecting matplotlib
  Using cached matplotlib-3.4.1-cp37-cp37m-win_amd64.whl (7.1 MB)
Collecting Cython
  Using cached Cython-0.29.22-cp37-cp37m-win_amd64.whl (1.6 MB)
Collecting contextlib2
  Downloading contextlib2-0.6.0.post1-py2.py3-none-any.whl (9.8 kB)
Collecting tf-slim
  Downloading tf_slim-1.1.0-py2.py3-none-any.whl (352 kB)
     |████████████████████████████████| 352 kB 6.4 MB/s
Requirement already satisfied: six in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from object-detection==0.1) (1.15.0)
Collecting pycocotools
  Using cached pycocotools-2.0.2-cp37-cp37m-win_amd64.whl
Collecting lvis
  Downloading lvis-0.5.3-py3-none-any.whl (14 kB)
Collecting scipy
  Using cached scipy-1.6.2-cp37-cp37m-win_amd64.whl (32.6 MB)
Collecting pandas
  Downloading pandas-1.2.3-cp37-cp37m-win_amd64.whl (9.1 MB)
     |████████████████████████████████| 9.1 MB 6.4 MB/s
Collecting tf-models-official
  Downloading tf_models_official-2.4.0-py2.py3-none-any.whl (1.1 MB)
     |████████████████████████████████| 1.1 MB ...
Collecting avro-python3
  Downloading avro-python3-1.9.2.1.tar.gz (37 kB)
Collecting dill<0.3.2,>=0.3.1.1
  Downloading dill-0.3.1.1.tar.gz (151 kB)
     |████████████████████████████████| 151 kB ...
Collecting crcmod<2.0,>=1.7
  Downloading crcmod-1.7.tar.gz (89 kB)
     |████████████████████████████████| 89 kB 6.1 MB/s
Requirement already satisfied: requests<3.0.0,>=2.24.0 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from apache-beam->object-detection==0.1) (2.25.1)
Collecting oauth2client<5,>=2.0.1
  Downloading oauth2client-4.1.3-py2.py3-none-any.whl (98 kB)
     |████████████████████████████████| 98 kB 3.8 MB/s
Requirement already satisfied: protobuf<4,>=3.12.2 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from apache-beam->object-detection==0.1) (3.15.8)
Requirement already satisfied: numpy<1.20.0,>=1.14.3 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from apache-beam->object-detection==0.1) (1.18.5)
Collecting pytz>=2018.3
  Using cached pytz-2021.1-py2.py3-none-any.whl (510 kB)
Collecting fastavro<2,>=0.21.4
  Downloading fastavro-1.3.5-cp37-cp37m-win_amd64.whl (392 kB)
     |████████████████████████████████| 392 kB 6.4 MB/s
Collecting pymongo<4.0.0,>=3.8.0
  Downloading pymongo-3.11.3-cp37-cp37m-win_amd64.whl (382 kB)
     |████████████████████████████████| 382 kB 107 kB/s
Collecting python-dateutil<3,>=2.8.0
  Using cached python_dateutil-2.8.1-py2.py3-none-any.whl (227 kB)
Collecting future<1.0.0,>=0.18.2
  Using cached future-0.18.2.tar.gz (829 kB)
Collecting mock<3.0.0,>=1.0.1
  Downloading mock-2.0.0-py2.py3-none-any.whl (56 kB)
     |████████████████████████████████| 56 kB ...
Requirement already satisfied: grpcio<2,>=1.29.0 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from apache-beam->object-detection==0.1) (1.37.0)
Requirement already satisfied: typing-extensions<3.8.0,>=3.7.0 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from apache-beam->object-detection==0.1) (3.7.4.3)
Collecting hdfs<3.0.0,>=2.1.0
  Downloading hdfs-2.6.0-py3-none-any.whl (33 kB)
Collecting httplib2<0.18.0,>=0.8
  Downloading httplib2-0.17.4-py3-none-any.whl (95 kB)
     |████████████████████████████████| 95 kB 2.0 MB/s
Collecting pyarrow<3.0.0,>=0.15.1
  Downloading pyarrow-2.0.0-cp37-cp37m-win_amd64.whl (10.7 MB)
     |████████████████████████████████| 10.7 MB 3.3 MB/s
Collecting pydot<2,>=1.2.0
  Downloading pydot-1.4.2-py2.py3-none-any.whl (21 kB)
Collecting docopt
  Using cached docopt-0.6.2.tar.gz (25 kB)
Collecting pbr>=0.11
  Downloading pbr-5.5.1-py2.py3-none-any.whl (106 kB)
     |████████████████████████████████| 106 kB 6.8 MB/s
Requirement already satisfied: pyasn1>=0.1.7 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from oauth2client<5,>=2.0.1->apache-beam->object-detection==0.1) (0.4.8)
Requirement already satisfied: pyasn1-modules>=0.0.5 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from oauth2client<5,>=2.0.1->apache-beam->object-detection==0.1) (0.2.8)
Requirement already satisfied: rsa>=3.1.4 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from oauth2client<5,>=2.0.1->apache-beam->object-detection==0.1) (4.7.2)
Collecting pyparsing>=2.1.4
  Using cached pyparsing-2.4.7-py2.py3-none-any.whl (67 kB)
Requirement already satisfied: chardet<5,>=3.0.2 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from requests<3.0.0,>=2.24.0->apache-beam->object-detection==0.1) (4.0.0)
Requirement already satisfied: certifi>=2017.4.17 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from requests<3.0.0,>=2.24.0->apache-beam->object-detection==0.1) (2020.12.5)
Requirement already satisfied: idna<3,>=2.5 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from requests<3.0.0,>=2.24.0->apache-beam->object-detection==0.1) (2.10)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from requests<3.0.0,>=2.24.0->apache-beam->object-detection==0.1) (1.26.4)
Collecting cycler>=0.10.0
  Using cached cycler-0.10.0-py2.py3-none-any.whl (6.5 kB)
Collecting opencv-python>=4.1.0.25
  Using cached opencv_python-4.5.1.48-cp37-cp37m-win_amd64.whl (34.9 MB)
Collecting kiwisolver>=1.1.0
  Using cached kiwisolver-1.3.1-cp37-cp37m-win_amd64.whl (51 kB)
Requirement already satisfied: setuptools>=18.0 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from pycocotools->object-detection==0.1) (52.0.0.post20210125)
Collecting psutil>=5.4.3
  Downloading psutil-5.8.0-cp37-cp37m-win_amd64.whl (244 kB)
     |████████████████████████████████| 244 kB 6.8 MB/s
Collecting tensorflow-model-optimization>=0.4.1
  Downloading tensorflow_model_optimization-0.5.0-py2.py3-none-any.whl (172 kB)
     |████████████████████████████████| 172 kB 6.8 MB/s
Collecting sentencepiece
  Downloading sentencepiece-0.1.95-cp37-cp37m-win_amd64.whl (1.2 MB)
     |████████████████████████████████| 1.2 MB 6.8 MB/s
Collecting seqeval
  Downloading seqeval-1.2.2.tar.gz (43 kB)
     |████████████████████████████████| 43 kB ...
Collecting tensorflow>=2.4.0
  Downloading tensorflow-2.4.1-cp37-cp37m-win_amd64.whl (370.7 MB)
     |████████████████████████████████| 370.7 MB 144 kB/s
Collecting google-api-python-client>=1.6.7
  Downloading google_api_python_client-2.1.0-py2.py3-none-any.whl (6.6 MB)
     |████████████████████████████████| 6.6 MB 6.4 MB/s
Collecting dataclasses
  Downloading dataclasses-0.6-py3-none-any.whl (14 kB)
Collecting tensorflow-addons
  Downloading tensorflow_addons-0.12.1-cp37-cp37m-win_amd64.whl (639 kB)
     |████████████████████████████████| 639 kB 6.4 MB/s
Collecting tensorflow-datasets
  Downloading tensorflow_datasets-4.2.0-py3-none-any.whl (3.7 MB)
     |████████████████████████████████| 3.7 MB 6.4 MB/s
Collecting gin-config
  Downloading gin_config-0.4.0-py2.py3-none-any.whl (46 kB)
     |████████████████████████████████| 46 kB 1.6 MB/s
Collecting tensorflow-hub>=0.6.0
  Downloading tensorflow_hub-0.11.0-py2.py3-none-any.whl (107 kB)
     |████████████████████████████████| 107 kB 6.4 MB/s
Collecting opencv-python-headless
  Downloading opencv_python_headless-4.5.1.48-cp37-cp37m-win_amd64.whl (34.8 MB)
     |████████████████████████████████| 34.8 MB 6.4 MB/s
Collecting google-cloud-bigquery>=0.31.0
  Downloading google_cloud_bigquery-2.13.1-py2.py3-none-any.whl (216 kB)
     |████████████████████████████████| 216 kB ...
Collecting py-cpuinfo>=3.3.0
  Downloading py-cpuinfo-7.0.0.tar.gz (95 kB)
     |████████████████████████████████| 95 kB 2.5 MB/s
Collecting kaggle>=1.3.9
  Downloading kaggle-1.5.12.tar.gz (58 kB)
     |████████████████████████████████| 58 kB 4.1 MB/s
Collecting pyyaml>=5.1
  Using cached PyYAML-5.4.1-cp37-cp37m-win_amd64.whl (210 kB)
Collecting google-auth-httplib2>=0.1.0
  Downloading google_auth_httplib2-0.1.0-py2.py3-none-any.whl (9.3 kB)
Collecting google-api-core<2dev,>=1.21.0
  Downloading google_api_core-1.26.3-py2.py3-none-any.whl (93 kB)
     |████████████████████████████████| 93 kB 528 kB/s
Collecting uritemplate<4dev,>=3.0.0
  Downloading uritemplate-3.0.1-py2.py3-none-any.whl (15 kB)
Requirement already satisfied: google-auth<2dev,>=1.16.0 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from google-api-python-client>=1.6.7->tf-models-official->object-detection==0.1) (1.28.1)
Collecting packaging>=14.3
  Downloading packaging-20.9-py2.py3-none-any.whl (40 kB)
     |████████████████████████████████| 40 kB 2.7 MB/s
Collecting googleapis-common-protos<2.0dev,>=1.6.0
  Downloading googleapis_common_protos-1.53.0-py2.py3-none-any.whl (198 kB)
     |████████████████████████████████| 198 kB 6.8 MB/s
Requirement already satisfied: cachetools<5.0,>=2.0.0 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from google-auth<2dev,>=1.16.0->google-api-python-client>=1.6.7->tf-models-official->object-detection==0.1) (4.2.1)
Collecting proto-plus>=1.10.0
  Downloading proto_plus-1.18.1-py3-none-any.whl (42 kB)
     |████████████████████████████████| 42 kB ...
Collecting google-cloud-core<2.0dev,>=1.4.1
  Downloading google_cloud_core-1.6.0-py2.py3-none-any.whl (28 kB)
Collecting google-resumable-media<2.0dev,>=0.6.0
  Downloading google_resumable_media-1.2.0-py2.py3-none-any.whl (75 kB)
     |████████████████████████████████| 75 kB 1.5 MB/s
Collecting google-crc32c<2.0dev,>=1.0
  Downloading google_crc32c-1.1.2-cp37-cp37m-win_amd64.whl (34 kB)
Collecting cffi>=1.0.0
  Downloading cffi-1.14.5-cp37-cp37m-win_amd64.whl (178 kB)
     |████████████████████████████████| 178 kB 6.4 MB/s
Collecting pycparser
  Downloading pycparser-2.20-py2.py3-none-any.whl (112 kB)
     |████████████████████████████████| 112 kB 6.8 MB/s
Collecting tqdm
  Downloading tqdm-4.60.0-py2.py3-none-any.whl (75 kB)
     |████████████████████████████████| 75 kB 2.0 MB/s
Collecting python-slugify
  Downloading python-slugify-4.0.1.tar.gz (11 kB)
Collecting tensorflow-estimator<2.5.0,>=2.4.0
  Using cached tensorflow_estimator-2.4.0-py2.py3-none-any.whl (462 kB)
Collecting numpy<1.20.0,>=1.14.3
  Using cached numpy-1.19.5-cp37-cp37m-win_amd64.whl (13.2 MB)
Requirement already satisfied: opt-einsum~=3.3.0 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (3.3.0)
Collecting flatbuffers~=1.12.0
  Using cached flatbuffers-1.12-py2.py3-none-any.whl (15 kB)
Requirement already satisfied: google-pasta~=0.2 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (0.2.0)
Requirement already satisfied: wheel~=0.35 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (0.36.2)
Collecting tensorboard~=2.4
  Using cached tensorboard-2.4.1-py3-none-any.whl (10.6 MB)
Requirement already satisfied: termcolor~=1.1.0 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (1.1.0)
Collecting grpcio<2,>=1.29.0
  Using cached grpcio-1.32.0-cp37-cp37m-win_amd64.whl (2.5 MB)
Requirement already satisfied: astunparse~=1.6.3 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (1.6.3)
Requirement already satisfied: gast==0.3.3 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (0.3.3)
Requirement already satisfied: keras-preprocessing~=1.1.2 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (1.1.2)
Requirement already satisfied: h5py~=2.10.0 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (2.10.0)
Requirement already satisfied: wrapt~=1.12.1 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (1.12.1)
Requirement already satisfied: absl-py~=0.10 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (0.12.0)
Requirement already satisfied: markdown>=2.6.8 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from tensorboard~=2.4->tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (3.3.4)
Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from tensorboard~=2.4->tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (0.4.4)
Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from tensorboard~=2.4->tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (1.8.0)
Requirement already satisfied: werkzeug>=0.11.15 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from tensorboard~=2.4->tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (1.0.1)
Requirement already satisfied: requests-oauthlib>=0.7.0 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard~=2.4->tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (1.3.0)
Requirement already satisfied: importlib-metadata in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from markdown>=2.6.8->tensorboard~=2.4->tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (3.10.0)
Requirement already satisfied: oauthlib>=3.0.0 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard~=2.4->tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (3.1.0)
Collecting dm-tree~=0.1.1
  Downloading dm_tree-0.1.5-cp37-cp37m-win_amd64.whl (86 kB)
     |████████████████████████████████| 86 kB 2.3 MB/s
Requirement already satisfied: zipp>=0.5 in e:\anaconda3\install\envs\wind_202103\lib\site-packages (from importlib-metadata->markdown>=2.6.8->tensorboard~=2.4->tensorflow>=2.4.0->tf-models-official->object-detection==0.1) (3.4.1)
Collecting text-unidecode>=1.3
  Downloading text_unidecode-1.3-py2.py3-none-any.whl (78 kB)
     |████████████████████████████████| 78 kB 5.5 MB/s
Collecting scikit-learn>=0.21.3
  Downloading scikit_learn-0.24.1-cp37-cp37m-win_amd64.whl (6.8 MB)
     |████████████████████████████████| 6.8 MB 364 kB/s
Collecting threadpoolctl>=2.0.0
  Using cached threadpoolctl-2.1.0-py3-none-any.whl (12 kB)
Collecting joblib>=0.11
  Using cached joblib-1.0.1-py3-none-any.whl (303 kB)
Collecting typeguard>=2.7
  Downloading typeguard-2.12.0-py3-none-any.whl (16 kB)
Collecting promise
  Downloading promise-2.3.tar.gz (19 kB)
Collecting tensorflow-metadata
  Downloading tensorflow_metadata-0.29.0-py3-none-any.whl (47 kB)
     |████████████████████████████████| 47 kB 3.4 MB/s
Collecting importlib-resources
  Downloading importlib_resources-5.1.2-py3-none-any.whl (25 kB)
Collecting attrs>=18.1.0
  Downloading attrs-20.3.0-py2.py3-none-any.whl (49 kB)
     |████████████████████████████████| 49 kB 3.2 MB/s
Building wheels for collected packages: object-detection, avro-python3, crcmod, dill, future, docopt, kaggle, py-cpuinfo, python-slugify, seqeval, promise
  Building wheel for object-detection (setup.py) ... done
  Created wheel for object-detection: filename=object_detection-0.1-py3-none-any.whl size=1644003 sha256=438ab0e3fe0a1444bda2014d6b11b91cf2a93d5bfb3f2ffc72def1cddfdcb50e
  Stored in directory: C:\Users\BIM\AppData\Local\Temp\pip-ephem-wheel-cache-607bho7i\wheels\25\df\7c\f10d33cbbded9d858ca0ec5852c4e6448ff366dbf648d5b9f1
  Building wheel for avro-python3 (setup.py) ... done
  Created wheel for avro-python3: filename=avro_python3-1.9.2.1-py3-none-any.whl size=43512 sha256=6eb1f83c9134b65a46b01a138e1469ed320efca1443d47d9c041f734dafb0ac8
  Stored in directory: c:\users\bim\appdata\local\pip\cache\wheels\bc\49\5f\fdb5b9d85055c478213e0158ac122b596816149a02d82e0ab1
  Building wheel for crcmod (setup.py) ... done
  Created wheel for crcmod: filename=crcmod-1.7-cp37-cp37m-win_amd64.whl size=25420 sha256=48b89fa8ca6178c41b06803b0fdf4c610640ac2f793003a5b51cf5424c1becc9
  Stored in directory: c:\users\bim\appdata\local\pip\cache\wheels\dc\9a\e9\49e627353476cec8484343c4ab656f1e0d783ee77b9dde2d1f
  Building wheel for dill (setup.py) ... done
  Created wheel for dill: filename=dill-0.3.1.1-py3-none-any.whl size=78594 sha256=01257f3976c005d253761dea76934a2044123e1d0ce6cf84e322df14410c2679
  Stored in directory: c:\users\bim\appdata\local\pip\cache\wheels\a4\61\fd\c57e374e580aa78a45ed78d5859b3a44436af17e22ca53284f
  Building wheel for future (setup.py) ... done
  Created wheel for future: filename=future-0.18.2-py3-none-any.whl size=491059 sha256=4641c73010c95644a52b1fa468d6b80de84a62d2028364d4a02cfd3165bb4e62
  Stored in directory: c:\users\bim\appdata\local\pip\cache\wheels\56\b0\fe\4410d17b32f1f0c3cf54cdfb2bc04d7b4b8f4ae377e2229ba0
  Building wheel for docopt (setup.py) ... done
  Created wheel for docopt: filename=docopt-0.6.2-py2.py3-none-any.whl size=13705 sha256=5a922722c8b4c65acafaeec8e23bf986e6301f89592770ca86269850e5eafe24
  Stored in directory: c:\users\bim\appdata\local\pip\cache\wheels\72\b0\3f\1d95f96ff986c7dfffe46ce2be4062f38ebd04b506c77c81b9
  Building wheel for kaggle (setup.py) ... done
  Created wheel for kaggle: filename=kaggle-1.5.12-py3-none-any.whl size=73053 sha256=2a2a466c0c45560892582652a4f63d22bedf5cbef7b91647be6336a83284310e
  Stored in directory: c:\users\bim\appdata\local\pip\cache\wheels\62\d6\58\5853130f941e75b2177d281eb7e44b4a98ed46dd155f556dc5
  Building wheel for py-cpuinfo (setup.py) ... done
  Created wheel for py-cpuinfo: filename=py_cpuinfo-7.0.0-py3-none-any.whl size=20070 sha256=e7092a7bc641e8e35d4793d50cca2616e37be2995fff5efd60697750b46c8cf8
  Stored in directory: c:\users\bim\appdata\local\pip\cache\wheels\d7\59\0d\58c5e576d9192261fa3da00466eebe6f7a1ac1873a7ab1f2ce
  Building wheel for python-slugify (setup.py) ... done
  Created wheel for python-slugify: filename=python_slugify-4.0.1-py2.py3-none-any.whl size=6769 sha256=a4e531b0f66f13c3912cd45958658f9dca9eeb63b8b860b91454e603ad44fb8b
  Stored in directory: c:\users\bim\appdata\local\pip\cache\wheels\48\1b\6f\5c1cfab22eacbe0095fc619786da6571b55253653c71324b5c
  Building wheel for seqeval (setup.py) ... done
  Created wheel for seqeval: filename=seqeval-1.2.2-py3-none-any.whl size=16170 sha256=baedbd5afa3f6f4055c397f2fa6841567fb6c7f00e85a226ef39c6205b7bb38d
  Stored in directory: c:\users\bim\appdata\local\pip\cache\wheels\05\96\ee\7cac4e74f3b19e3158dce26a20a1c86b3533c43ec72a549fd7
  Building wheel for promise (setup.py) ... done
  Created wheel for promise: filename=promise-2.3-py3-none-any.whl size=21494 sha256=703d5207d84c2fa8a8024975cf73faa11af98e895627f47fdf537b099cc61289
  Stored in directory: c:\users\bim\appdata\local\pip\cache\wheels\29\93\c6\762e359f8cb6a5b69c72235d798804cae523bbe41c2aa8333d
Successfully built object-detection avro-python3 crcmod dill future docopt kaggle py-cpuinfo python-slugify seqeval promise
Installing collected packages: pyparsing, pycparser, pytz, packaging, numpy, googleapis-common-protos, cffi, threadpoolctl, text-unidecode, scipy, python-dateutil, pillow, kiwisolver, joblib, httplib2, grpcio, google-crc32c, google-api-core, cycler, uritemplate, typeguard, tqdm, tensorflow-metadata, tensorflow-estimator, tensorboard, scikit-learn, python-slugify, proto-plus, promise, pbr, matplotlib, importlib-resources, google-resumable-media, google-cloud-core, google-auth-httplib2, future, flatbuffers, docopt, dm-tree, dill, Cython, attrs, tf-slim, tensorflow-model-optimization, tensorflow-hub, tensorflow-datasets, tensorflow-addons, tensorflow, seqeval, sentencepiece, pyyaml, pymongo, pydot, pycocotools, pyarrow, py-cpuinfo, psutil, pandas, opencv-python-headless, opencv-python, oauth2client, mock, kaggle, hdfs, google-cloud-bigquery, google-api-python-client, gin-config, fastavro, dataclasses, crcmod, avro-python3, tf-models-official, lxml, lvis, contextlib2, apache-beam, object-detection
  Attempting uninstall: numpy
    Found existing installation: numpy 1.18.5
    Uninstalling numpy-1.18.5:
      Successfully uninstalled numpy-1.18.5
  Attempting uninstall: grpcio
    Found existing installation: grpcio 1.37.0
    Uninstalling grpcio-1.37.0:
      Successfully uninstalled grpcio-1.37.0
  Attempting uninstall: tensorflow-estimator
    Found existing installation: tensorflow-estimator 2.2.0
    Uninstalling tensorflow-estimator-2.2.0:
      Successfully uninstalled tensorflow-estimator-2.2.0
  Attempting uninstall: tensorboard
    Found existing installation: tensorboard 2.2.2
    Uninstalling tensorboard-2.2.2:
      Successfully uninstalled tensorboard-2.2.2
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
tensorflow-cpu 2.2.2 requires numpy<1.19.0,>=1.16.0, but you have numpy 1.19.5 which is incompatible.
tensorflow-cpu 2.2.2 requires tensorboard<2.3.0,>=2.2.0, but you have tensorboard 2.4.1 which is incompatible.
tensorflow-cpu 2.2.2 requires tensorflow-estimator<2.3.0,>=2.2.0, but you have tensorflow-estimator 2.4.0 which is incompatible.
Successfully installed Cython-0.29.22 apache-beam-2.28.0 attrs-20.3.0 avro-python3-1.9.2.1 cffi-1.14.5 contextlib2-0.6.0.post1 crcmod-1.7 cycler-0.10.0 dataclasses-0.6 dill-0.3.1.1 dm-tree-0.1.5 docopt-0.6.2 fastavro-1.3.5 flatbuffers-1.12 future-0.18.2 gin-config-0.4.0 google-api-core-1.26.3 google-api-python-client-2.1.0 google-auth-httplib2-0.1.0 google-cloud-bigquery-2.13.1 google-cloud-core-1.6.0 google-crc32c-1.1.2 google-resumable-media-1.2.0 googleapis-common-protos-1.53.0 grpcio-1.32.0 hdfs-2.6.0 httplib2-0.17.4 importlib-resources-5.1.2 joblib-1.0.1 kaggle-1.5.12 kiwisolver-1.3.1 lvis-0.5.3 lxml-4.6.3 matplotlib-3.4.1 mock-2.0.0 numpy-1.19.5 oauth2client-4.1.3 object-detection-0.1 opencv-python-4.5.1.48 opencv-python-headless-4.5.1.48 packaging-20.9 pandas-1.2.3 pbr-5.5.1 pillow-8.2.0 promise-2.3 proto-plus-1.18.1 psutil-5.8.0 py-cpuinfo-7.0.0 pyarrow-2.0.0 pycocotools-2.0.2 pycparser-2.20 pydot-1.4.2 pymongo-3.11.3 pyparsing-2.4.7 python-dateutil-2.8.1 python-slugify-4.0.1 pytz-2021.1 pyyaml-5.4.1 scikit-learn-0.24.1 scipy-1.6.2 sentencepiece-0.1.95 seqeval-1.2.2 tensorboard-2.4.1 tensorflow-2.4.1 tensorflow-addons-0.12.1 tensorflow-datasets-4.2.0 tensorflow-estimator-2.4.0 tensorflow-hub-0.11.0 tensorflow-metadata-0.29.0 tensorflow-model-optimization-0.5.0 text-unidecode-1.3 tf-models-official-2.4.0 tf-slim-1.1.0 threadpoolctl-2.1.0 tqdm-4.60.0 typeguard-2.12.0 uritemplate-3.0.1

(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>

 

 

 测试

(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>python object_detection/builders/model_builder_tf2_test.py
2021-04-12 14:15:52.486730: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cudart64_110.dll
Running tests under Python 3.7.10: E:\Anaconda3\install\envs\wind_202103\python.exe
[ RUN      ] ModelBuilderTF2Test.test_create_center_net_model
2021-04-12 14:15:55.906964: I tensorflow/compiler/jit/xla_cpu_device.cc:41] Not creating XLA devices, tf_xla_enable_xla_devices not set
2021-04-12 14:15:55.914149: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library nvcuda.dll
2021-04-12 14:15:58.094186: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1720] Found device 0 with properties:
pciBusID: 0000:01:00.0 name: GeForce RTX 3080 Laptop GPU computeCapability: 8.6
coreClock: 1.245GHz coreCount: 48 deviceMemorySize: 16.00GiB deviceMemoryBandwidth: 357.69GiB/s
2021-04-12 14:15:58.094455: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cudart64_110.dll
2021-04-12 14:15:58.144854: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cublas64_11.dll
2021-04-12 14:15:58.144929: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cublasLt64_11.dll
2021-04-12 14:15:58.170496: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cufft64_10.dll
2021-04-12 14:15:58.178093: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library curand64_10.dll
2021-04-12 14:15:58.182160: W tensorflow/stream_executor/platform/default/dso_loader.cc:60] Could not load dynamic library 'cusolver64_10.dll'; dlerror: cusolver64_10.dll not found
2021-04-12 14:15:58.199838: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cusparse64_11.dll
2021-04-12 14:15:58.203486: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cudnn64_8.dll
2021-04-12 14:15:58.203589: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1757] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.
Skipping registering GPU devices...
2021-04-12 14:15:58.204149: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2021-04-12 14:15:58.204888: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1261] Device interconnect StreamExecutor with strength 1 edge matrix:
2021-04-12 14:15:58.207014: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1267]
2021-04-12 14:15:58.211032: I tensorflow/compiler/jit/xla_gpu_device.cc:99] Not creating XLA devices, tf_xla_enable_xla_devices not set
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_center_net_model): 2.91s
I0412 14:15:58.526351 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_center_net_model): 2.91s
[       OK ] ModelBuilderTF2Test.test_create_center_net_model
[ RUN      ] ModelBuilderTF2Test.test_create_center_net_model_from_keypoints
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_center_net_model_from_keypoints): 0.25s
I0412 14:15:58.776292 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_center_net_model_from_keypoints): 0.25s
[       OK ] ModelBuilderTF2Test.test_create_center_net_model_from_keypoints
[ RUN      ] ModelBuilderTF2Test.test_create_experimental_model
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_experimental_model): 0.0s
I0412 14:15:58.776292 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_experimental_model): 0.0s
[       OK ] ModelBuilderTF2Test.test_create_experimental_model
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature0 (True)
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature0 (True)): 0.03s
I0412 14:15:58.807536 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature0 (True)): 0.03s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature0 (True)
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature1 (False)
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature1 (False)): 0.02s
I0412 14:15:58.823157 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature1 (False)): 0.02s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature1 (False)
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_model_from_config_with_example_miner
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_model_from_config_with_example_miner): 0.02s
I0412 14:15:58.838778 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_model_from_config_with_example_miner): 0.02s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_model_from_config_with_example_miner
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul): 0.09s
I0412 14:15:58.932541 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul): 0.09s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul): 0.08s
I0412 14:15:59.027438 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul): 0.08s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul): 0.1s
I0412 14:15:59.138765 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul): 0.1s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul): 0.09s
I0412 14:15:59.232494 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul): 0.09s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul
[ RUN      ] ModelBuilderTF2Test.test_create_rfcn_model_from_config
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_rfcn_model_from_config): 0.09s
I0412 14:15:59.341844 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_rfcn_model_from_config): 0.09s
[       OK ] ModelBuilderTF2Test.test_create_rfcn_model_from_config
[ RUN      ] ModelBuilderTF2Test.test_create_ssd_fpn_model_from_config
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_ssd_fpn_model_from_config): 0.03s
I0412 14:15:59.374269 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_ssd_fpn_model_from_config): 0.03s
[       OK ] ModelBuilderTF2Test.test_create_ssd_fpn_model_from_config
[ RUN      ] ModelBuilderTF2Test.test_create_ssd_models_from_config
I0412 14:15:59.589379 11224 ssd_efficientnet_bifpn_feature_extractor.py:143] EfficientDet EfficientNet backbone version: efficientnet-b0
I0412 14:15:59.589379 11224 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet BiFPN num filters: 64
I0412 14:15:59.589379 11224 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet BiFPN num iterations: 3
I0412 14:15:59.589379 11224 efficientnet_model.py:147] round_filter input=32 output=32
I0412 14:15:59.605001 11224 efficientnet_model.py:147] round_filter input=32 output=32
I0412 14:15:59.605001 11224 efficientnet_model.py:147] round_filter input=16 output=16
I0412 14:15:59.636244 11224 efficientnet_model.py:147] round_filter input=16 output=16
I0412 14:15:59.636244 11224 efficientnet_model.py:147] round_filter input=24 output=24
I0412 14:15:59.746711 11224 efficientnet_model.py:147] round_filter input=24 output=24
I0412 14:15:59.746711 11224 efficientnet_model.py:147] round_filter input=40 output=40
I0412 14:15:59.847079 11224 efficientnet_model.py:147] round_filter input=40 output=40
I0412 14:15:59.847079 11224 efficientnet_model.py:147] round_filter input=80 output=80
I0412 14:16:00.003327 11224 efficientnet_model.py:147] round_filter input=80 output=80
I0412 14:16:00.003327 11224 efficientnet_model.py:147] round_filter input=112 output=112
I0412 14:16:00.160682 11224 efficientnet_model.py:147] round_filter input=112 output=112
I0412 14:16:00.160682 11224 efficientnet_model.py:147] round_filter input=192 output=192
I0412 14:16:00.420666 11224 efficientnet_model.py:147] round_filter input=192 output=192
I0412 14:16:00.420666 11224 efficientnet_model.py:147] round_filter input=320 output=320
I0412 14:16:00.484324 11224 efficientnet_model.py:147] round_filter input=1280 output=1280
I0412 14:16:00.515606 11224 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=1.0, depth_coefficient=1.0, resolution=224, dropout_rate=0.2, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0412 14:16:00.572247 11224 ssd_efficientnet_bifpn_feature_extractor.py:143] EfficientDet EfficientNet backbone version: efficientnet-b1
I0412 14:16:00.572247 11224 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet BiFPN num filters: 88
I0412 14:16:00.572247 11224 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet BiFPN num iterations: 4
I0412 14:16:00.572247 11224 efficientnet_model.py:147] round_filter input=32 output=32
I0412 14:16:00.587869 11224 efficientnet_model.py:147] round_filter input=32 output=32
I0412 14:16:00.587869 11224 efficientnet_model.py:147] round_filter input=16 output=16
I0412 14:16:00.665976 11224 efficientnet_model.py:147] round_filter input=16 output=16
I0412 14:16:00.665976 11224 efficientnet_model.py:147] round_filter input=24 output=24
I0412 14:16:00.822189 11224 efficientnet_model.py:147] round_filter input=24 output=24
I0412 14:16:00.822189 11224 efficientnet_model.py:147] round_filter input=40 output=40
I0412 14:16:00.981099 11224 efficientnet_model.py:147] round_filter input=40 output=40
I0412 14:16:00.981099 11224 efficientnet_model.py:147] round_filter input=80 output=80
I0412 14:16:01.184208 11224 efficientnet_model.py:147] round_filter input=80 output=80
I0412 14:16:01.184208 11224 efficientnet_model.py:147] round_filter input=112 output=112
I0412 14:16:01.391219 11224 efficientnet_model.py:147] round_filter input=112 output=112
I0412 14:16:01.391219 11224 efficientnet_model.py:147] round_filter input=192 output=192
I0412 14:16:01.672546 11224 efficientnet_model.py:147] round_filter input=192 output=192
I0412 14:16:01.672546 11224 efficientnet_model.py:147] round_filter input=320 output=320
I0412 14:16:01.801679 11224 efficientnet_model.py:147] round_filter input=1280 output=1280
I0412 14:16:01.832922 11224 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=1.0, depth_coefficient=1.1, resolution=240, dropout_rate=0.2, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0412 14:16:01.879786 11224 ssd_efficientnet_bifpn_feature_extractor.py:143] EfficientDet EfficientNet backbone version: efficientnet-b2
I0412 14:16:01.879786 11224 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet BiFPN num filters: 112
I0412 14:16:01.879786 11224 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet BiFPN num iterations: 5
I0412 14:16:01.895407 11224 efficientnet_model.py:147] round_filter input=32 output=32
I0412 14:16:01.895407 11224 efficientnet_model.py:147] round_filter input=32 output=32
I0412 14:16:01.911029 11224 efficientnet_model.py:147] round_filter input=16 output=16
I0412 14:16:01.989136 11224 efficientnet_model.py:147] round_filter input=16 output=16
I0412 14:16:01.989136 11224 efficientnet_model.py:147] round_filter input=24 output=24
I0412 14:16:02.130882 11224 efficientnet_model.py:147] round_filter input=24 output=24
I0412 14:16:02.130882 11224 efficientnet_model.py:147] round_filter input=40 output=48
I0412 14:16:02.293226 11224 efficientnet_model.py:147] round_filter input=40 output=48
I0412 14:16:02.293226 11224 efficientnet_model.py:147] round_filter input=80 output=88
I0412 14:16:02.497462 11224 efficientnet_model.py:147] round_filter input=80 output=88
I0412 14:16:02.497462 11224 efficientnet_model.py:147] round_filter input=112 output=120
I0412 14:16:02.780225 11224 efficientnet_model.py:147] round_filter input=112 output=120
I0412 14:16:02.780225 11224 efficientnet_model.py:147] round_filter input=192 output=208
I0412 14:16:03.053839 11224 efficientnet_model.py:147] round_filter input=192 output=208
I0412 14:16:03.053839 11224 efficientnet_model.py:147] round_filter input=320 output=352
I0412 14:16:03.178811 11224 efficientnet_model.py:147] round_filter input=1280 output=1408
I0412 14:16:03.210053 11224 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=1.1, depth_coefficient=1.2, resolution=260, dropout_rate=0.3, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0412 14:16:03.272538 11224 ssd_efficientnet_bifpn_feature_extractor.py:143] EfficientDet EfficientNet backbone version: efficientnet-b3
I0412 14:16:03.272538 11224 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet BiFPN num filters: 160
I0412 14:16:03.272538 11224 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet BiFPN num iterations: 6
I0412 14:16:03.288159 11224 efficientnet_model.py:147] round_filter input=32 output=40
I0412 14:16:03.288159 11224 efficientnet_model.py:147] round_filter input=32 output=40
I0412 14:16:03.288159 11224 efficientnet_model.py:147] round_filter input=16 output=24
I0412 14:16:03.367403 11224 efficientnet_model.py:147] round_filter input=16 output=24
I0412 14:16:03.367403 11224 efficientnet_model.py:147] round_filter input=24 output=32
I0412 14:16:03.525760 11224 efficientnet_model.py:147] round_filter input=24 output=32
I0412 14:16:03.525760 11224 efficientnet_model.py:147] round_filter input=40 output=48
I0412 14:16:03.681978 11224 efficientnet_model.py:147] round_filter input=40 output=48
I0412 14:16:03.681978 11224 efficientnet_model.py:147] round_filter input=80 output=96
I0412 14:16:03.936995 11224 efficientnet_model.py:147] round_filter input=80 output=96
I0412 14:16:03.936995 11224 efficientnet_model.py:147] round_filter input=112 output=136
I0412 14:16:04.211657 11224 efficientnet_model.py:147] round_filter input=112 output=136
I0412 14:16:04.211657 11224 efficientnet_model.py:147] round_filter input=192 output=232
I0412 14:16:04.560706 11224 efficientnet_model.py:147] round_filter input=192 output=232
I0412 14:16:04.560706 11224 efficientnet_model.py:147] round_filter input=320 output=384
I0412 14:16:04.701331 11224 efficientnet_model.py:147] round_filter input=1280 output=1536
I0412 14:16:04.732574 11224 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=1.2, depth_coefficient=1.4, resolution=300, dropout_rate=0.3, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0412 14:16:04.795061 11224 ssd_efficientnet_bifpn_feature_extractor.py:143] EfficientDet EfficientNet backbone version: efficientnet-b4
I0412 14:16:04.795061 11224 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet BiFPN num filters: 224
I0412 14:16:04.795061 11224 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet BiFPN num iterations: 7
I0412 14:16:04.795061 11224 efficientnet_model.py:147] round_filter input=32 output=48
I0412 14:16:04.810693 11224 efficientnet_model.py:147] round_filter input=32 output=48
I0412 14:16:04.810693 11224 efficientnet_model.py:147] round_filter input=16 output=24
I0412 14:16:04.889998 11224 efficientnet_model.py:147] round_filter input=16 output=24
I0412 14:16:04.889998 11224 efficientnet_model.py:147] round_filter input=24 output=32
I0412 14:16:05.079239 11224 efficientnet_model.py:147] round_filter input=24 output=32
I0412 14:16:05.079239 11224 efficientnet_model.py:147] round_filter input=40 output=56
I0412 14:16:05.410891 11224 efficientnet_model.py:147] round_filter input=40 output=56
I0412 14:16:05.410891 11224 efficientnet_model.py:147] round_filter input=80 output=112
I0412 14:16:05.725448 11224 efficientnet_model.py:147] round_filter input=80 output=112
I0412 14:16:05.725448 11224 efficientnet_model.py:147] round_filter input=112 output=160
I0412 14:16:06.054715 11224 efficientnet_model.py:147] round_filter input=112 output=160
I0412 14:16:06.054715 11224 efficientnet_model.py:147] round_filter input=192 output=272
I0412 14:16:06.576864 11224 efficientnet_model.py:147] round_filter input=192 output=272
I0412 14:16:06.576864 11224 efficientnet_model.py:147] round_filter input=320 output=448
I0412 14:16:06.717458 11224 efficientnet_model.py:147] round_filter input=1280 output=1792
I0412 14:16:06.749806 11224 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=1.4, depth_coefficient=1.8, resolution=380, dropout_rate=0.4, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0412 14:16:06.824114 11224 ssd_efficientnet_bifpn_feature_extractor.py:143] EfficientDet EfficientNet backbone version: efficientnet-b5
I0412 14:16:06.824114 11224 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet BiFPN num filters: 288
I0412 14:16:06.824114 11224 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet BiFPN num iterations: 7
I0412 14:16:06.824114 11224 efficientnet_model.py:147] round_filter input=32 output=48
I0412 14:16:06.839785 11224 efficientnet_model.py:147] round_filter input=32 output=48
I0412 14:16:06.839785 11224 efficientnet_model.py:147] round_filter input=16 output=24
I0412 14:16:06.964734 11224 efficientnet_model.py:147] round_filter input=16 output=24
I0412 14:16:06.964734 11224 efficientnet_model.py:147] round_filter input=24 output=40
I0412 14:16:07.215926 11224 efficientnet_model.py:147] round_filter input=24 output=40
I0412 14:16:07.215926 11224 efficientnet_model.py:147] round_filter input=40 output=64
I0412 14:16:07.462391 11224 efficientnet_model.py:147] round_filter input=40 output=64
I0412 14:16:07.462391 11224 efficientnet_model.py:147] round_filter input=80 output=128
I0412 14:16:07.847848 11224 efficientnet_model.py:147] round_filter input=80 output=128
I0412 14:16:07.847848 11224 efficientnet_model.py:147] round_filter input=112 output=176
I0412 14:16:08.227632 11224 efficientnet_model.py:147] round_filter input=112 output=176
I0412 14:16:08.227632 11224 efficientnet_model.py:147] round_filter input=192 output=304
I0412 14:16:08.935734 11224 efficientnet_model.py:147] round_filter input=192 output=304
I0412 14:16:08.935734 11224 efficientnet_model.py:147] round_filter input=320 output=512
I0412 14:16:09.201296 11224 efficientnet_model.py:147] round_filter input=1280 output=2048
I0412 14:16:09.248161 11224 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=1.6, depth_coefficient=2.2, resolution=456, dropout_rate=0.4, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0412 14:16:09.327469 11224 ssd_efficientnet_bifpn_feature_extractor.py:143] EfficientDet EfficientNet backbone version: efficientnet-b6
I0412 14:16:09.327469 11224 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet BiFPN num filters: 384
I0412 14:16:09.327469 11224 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet BiFPN num iterations: 8
I0412 14:16:09.330456 11224 efficientnet_model.py:147] round_filter input=32 output=56
I0412 14:16:09.330456 11224 efficientnet_model.py:147] round_filter input=32 output=56
I0412 14:16:09.330456 11224 efficientnet_model.py:147] round_filter input=16 output=32
I0412 14:16:09.455431 11224 efficientnet_model.py:147] round_filter input=16 output=32
I0412 14:16:09.455431 11224 efficientnet_model.py:147] round_filter input=24 output=40
I0412 14:16:09.769093 11224 efficientnet_model.py:147] round_filter input=24 output=40
I0412 14:16:09.769093 11224 efficientnet_model.py:147] round_filter input=40 output=72
I0412 14:16:10.072026 11224 efficientnet_model.py:147] round_filter input=40 output=72
I0412 14:16:10.072026 11224 efficientnet_model.py:147] round_filter input=80 output=144
I0412 14:16:10.504786 11224 efficientnet_model.py:147] round_filter input=80 output=144
I0412 14:16:10.504786 11224 efficientnet_model.py:147] round_filter input=112 output=200
I0412 14:16:10.973426 11224 efficientnet_model.py:147] round_filter input=112 output=200
I0412 14:16:10.973426 11224 efficientnet_model.py:147] round_filter input=192 output=344
I0412 14:16:11.731940 11224 efficientnet_model.py:147] round_filter input=192 output=344
I0412 14:16:11.731940 11224 efficientnet_model.py:147] round_filter input=320 output=576
I0412 14:16:12.084060 11224 efficientnet_model.py:147] round_filter input=1280 output=2304
I0412 14:16:12.130926 11224 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=1.8, depth_coefficient=2.6, resolution=528, dropout_rate=0.5, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0412 14:16:12.209056 11224 ssd_efficientnet_bifpn_feature_extractor.py:143] EfficientDet EfficientNet backbone version: efficientnet-b7
I0412 14:16:12.209056 11224 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet BiFPN num filters: 384
I0412 14:16:12.224833 11224 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet BiFPN num iterations: 8
I0412 14:16:12.224833 11224 efficientnet_model.py:147] round_filter input=32 output=64
I0412 14:16:12.224833 11224 efficientnet_model.py:147] round_filter input=32 output=64
I0412 14:16:12.224833 11224 efficientnet_model.py:147] round_filter input=16 output=32
I0412 14:16:12.388885 11224 efficientnet_model.py:147] round_filter input=16 output=32
I0412 14:16:12.388885 11224 efficientnet_model.py:147] round_filter input=24 output=48
I0412 14:16:12.748528 11224 efficientnet_model.py:147] round_filter input=24 output=48
I0412 14:16:12.748528 11224 efficientnet_model.py:147] round_filter input=40 output=80
I0412 14:16:13.119887 11224 efficientnet_model.py:147] round_filter input=40 output=80
I0412 14:16:13.119887 11224 efficientnet_model.py:147] round_filter input=80 output=160
I0412 14:16:13.672224 11224 efficientnet_model.py:147] round_filter input=80 output=160
I0412 14:16:13.672224 11224 efficientnet_model.py:147] round_filter input=112 output=224
I0412 14:16:14.254858 11224 efficientnet_model.py:147] round_filter input=112 output=224
I0412 14:16:14.254858 11224 efficientnet_model.py:147] round_filter input=192 output=384
I0412 14:16:15.250613 11224 efficientnet_model.py:147] round_filter input=192 output=384
I0412 14:16:15.250613 11224 efficientnet_model.py:147] round_filter input=320 output=640
I0412 14:16:15.611495 11224 efficientnet_model.py:147] round_filter input=1280 output=2560
I0412 14:16:15.658359 11224 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=2.0, depth_coefficient=3.1, resolution=600, dropout_rate=0.5, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_ssd_models_from_config): 16.39s
I0412 14:16:15.767739 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_create_ssd_models_from_config): 16.39s
[       OK ] ModelBuilderTF2Test.test_create_ssd_models_from_config
[ RUN      ] ModelBuilderTF2Test.test_invalid_faster_rcnn_batchnorm_update
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_invalid_faster_rcnn_batchnorm_update): 0.0s
I0412 14:16:15.767739 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_invalid_faster_rcnn_batchnorm_update): 0.0s
[       OK ] ModelBuilderTF2Test.test_invalid_faster_rcnn_batchnorm_update
[ RUN      ] ModelBuilderTF2Test.test_invalid_first_stage_nms_iou_threshold
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_invalid_first_stage_nms_iou_threshold): 0.0s
I0412 14:16:15.783332 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_invalid_first_stage_nms_iou_threshold): 0.0s
[       OK ] ModelBuilderTF2Test.test_invalid_first_stage_nms_iou_threshold
[ RUN      ] ModelBuilderTF2Test.test_invalid_model_config_proto
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_invalid_model_config_proto): 0.0s
I0412 14:16:15.792893 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_invalid_model_config_proto): 0.0s
[       OK ] ModelBuilderTF2Test.test_invalid_model_config_proto
[ RUN      ] ModelBuilderTF2Test.test_invalid_second_stage_batch_size
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_invalid_second_stage_batch_size): 0.0s
I0412 14:16:15.796538 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_invalid_second_stage_batch_size): 0.0s
[       OK ] ModelBuilderTF2Test.test_invalid_second_stage_batch_size
[ RUN      ] ModelBuilderTF2Test.test_session
[  SKIPPED ] ModelBuilderTF2Test.test_session
[ RUN      ] ModelBuilderTF2Test.test_unknown_faster_rcnn_feature_extractor
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_unknown_faster_rcnn_feature_extractor): 0.0s
I0412 14:16:15.801620 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_unknown_faster_rcnn_feature_extractor): 0.0s
[       OK ] ModelBuilderTF2Test.test_unknown_faster_rcnn_feature_extractor
[ RUN      ] ModelBuilderTF2Test.test_unknown_meta_architecture
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_unknown_meta_architecture): 0.0s
I0412 14:16:15.803169 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_unknown_meta_architecture): 0.0s
[       OK ] ModelBuilderTF2Test.test_unknown_meta_architecture
[ RUN      ] ModelBuilderTF2Test.test_unknown_ssd_feature_extractor
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_unknown_ssd_feature_extractor): 0.0s
I0412 14:16:15.805706 11224 test_util.py:2076] time(__main__.ModelBuilderTF2Test.test_unknown_ssd_feature_extractor): 0.0s
[       OK ] ModelBuilderTF2Test.test_unknown_ssd_feature_extractor
----------------------------------------------------------------------
Ran 21 tests in 20.176s

OK (skipped=1)

(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>
(wind_202103) F:\TensorflowProject\models-master\research>

 

 

###########