Üye
Microsoft Windows [Version 10.0.18362.30]
(c) 2019 Microsoft Corporation. All rights reserved.
(c) 2019 Microsoft Corporation. All rights reserved.
Kod:
E:\PROJECTS\PYTHON\Diabetic_Retinopathy_Detection\Deep_Learning\Code_FINAL\MobileNet_based\code>C:/Users/Prashant/Anaconda3/Scripts/activate
(base) E:\PROJECTS\PYTHON\Diabetic_Retinopathy_Detection\Deep_Learning\Code_FINAL\MobileNet_based\code>conda activate gputest
(gputest) E:\PROJECTS\PYTHON\Diabetic_Retinopathy_Detection\Deep_Learning\Code_FINAL\MobileNet_based\code>C:/Users/Prashant/Anaconda3/envs/gputest/python.exe e:/PROJECTS/PYTHON/Diabetic_Retinopathy_Detection/Deep_Learning/Code_FINAL/MobileNet_based/code/model.py
Using TensorFlow backend.
2019-12-03 00:05:36.740990: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll
2019-12-03 00:05:39.114372: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library nvcuda.dll
2019-12-03 00:05:39.141749: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
name: GeForce GTX 1060 6GB major: 6 minor: 1 memoryClockRate(GHz): 1.7085
pciBusID: 0000:01:00.0
2019-12-03 00:05:39.147693: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check.
2019-12-03 00:05:39.158449: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2019-12-03 00:05:39.165781: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2
2019-12-03 00:05:39.177845: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
name: GeForce GTX 1060 6GB major: 6 minor: 1 memoryClockRate(GHz): 1.7085
pciBusID: 0000:01:00.0
2019-12-03 00:05:39.193251: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check.
2019-12-03 00:05:39.197264: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2019-12-03 00:05:42.916711: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-12-03 00:05:42.922258: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0
2019-12-03 00:05:42.924190: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N
2019-12-03 00:05:42.929023: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4708 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060 6GB, pci bus id: 0000:01:00.0, compute capability: 6.1)
Found 31563 images belonging to 5 classes.
Found 3507 images belonging to 5 classes.
Found 3507 images belonging to 5 classes.
Model: "mobilenet_1.00_224"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 224, 224, 3) 0
_________________________________________________________________
conv1_pad (ZeroPadding2D) (None, 225, 225, 3) 0
_________________________________________________________________
conv1 (Conv2D) (None, 112, 112, 32) 864
_________________________________________________________________
conv1_bn (BatchNormalization (None, 112, 112, 32) 128
_________________________________________________________________
conv1_relu (ReLU) (None, 112, 112, 32) 0
_________________________________________________________________
conv_dw_1 (DepthwiseConv2D) (None, 112, 112, 32) 288
_________________________________________________________________
conv_dw_1_bn (BatchNormaliza (None, 112, 112, 32) 128
_________________________________________________________________
conv_dw_1_relu (ReLU) (None, 112, 112, 32) 0
_________________________________________________________________
conv_pw_1 (Conv2D) (None, 112, 112, 64) 2048
_________________________________________________________________
conv_pw_1_bn (BatchNormaliza (None, 112, 112, 64) 256
_________________________________________________________________
conv_pw_1_relu (ReLU) (None, 112, 112, 64) 0
_________________________________________________________________
conv_pad_2 (ZeroPadding2D) (None, 113, 113, 64) 0
_________________________________________________________________
conv_dw_2 (DepthwiseConv2D) (None, 56, 56, 64) 576
_________________________________________________________________
conv_dw_2_bn (BatchNormaliza (None, 56, 56, 64) 256
_________________________________________________________________
conv_dw_2_relu (ReLU) (None, 56, 56, 64) 0
_________________________________________________________________
conv_pw_2 (Conv2D) (None, 56, 56, 128) 8192
_________________________________________________________________
conv_pw_2_bn (BatchNormaliza (None, 56, 56, 128) 512
_________________________________________________________________
conv_pw_2_relu (ReLU) (None, 56, 56, 128) 0
_________________________________________________________________
conv_dw_3 (DepthwiseConv2D) (None, 56, 56, 128) 1152
_________________________________________________________________
conv_dw_3_bn (BatchNormaliza (None, 56, 56, 128) 512
_________________________________________________________________
conv_dw_3_relu (ReLU) (None, 56, 56, 128) 0
_________________________________________________________________
conv_pw_3 (Conv2D) (None, 56, 56, 128) 16384
_________________________________________________________________
conv_pw_3_bn (BatchNormaliza (None, 56, 56, 128) 512
_________________________________________________________________
conv_pw_3_relu (ReLU) (None, 56, 56, 128) 0
_________________________________________________________________
conv_pad_4 (ZeroPadding2D) (None, 57, 57, 128) 0
_________________________________________________________________
conv_dw_4 (DepthwiseConv2D) (None, 28, 28, 128) 1152
_________________________________________________________________
conv_dw_4_bn (BatchNormaliza (None, 28, 28, 128) 512
_________________________________________________________________
conv_dw_4_relu (ReLU) (None, 28, 28, 128) 0
_________________________________________________________________
conv_pw_4 (Conv2D) (None, 28, 28, 256) 32768
_________________________________________________________________
conv_pw_4_bn (BatchNormaliza (None, 28, 28, 256) 1024
_________________________________________________________________
conv_pw_4_relu (ReLU) (None, 28, 28, 256) 0
_________________________________________________________________
conv_dw_5 (DepthwiseConv2D) (None, 28, 28, 256) 2304
_________________________________________________________________
conv_dw_5_bn (BatchNormaliza (None, 28, 28, 256) 1024
_________________________________________________________________
conv_dw_5_relu (ReLU) (None, 28, 28, 256) 0
_________________________________________________________________
conv_pw_5 (Conv2D) (None, 28, 28, 256) 65536
_________________________________________________________________
conv_pw_5_bn (BatchNormaliza (None, 28, 28, 256) 1024
_________________________________________________________________
conv_pw_5_relu (ReLU) (None, 28, 28, 256) 0
_________________________________________________________________
conv_pad_6 (ZeroPadding2D) (None, 29, 29, 256) 0
_________________________________________________________________
conv_dw_6 (DepthwiseConv2D) (None, 14, 14, 256) 2304
_________________________________________________________________
conv_dw_6_bn (BatchNormaliza (None, 14, 14, 256) 1024
_________________________________________________________________
conv_dw_6_relu (ReLU) (None, 14, 14, 256) 0
_________________________________________________________________
conv_pw_6 (Conv2D) (None, 14, 14, 512) 131072
_________________________________________________________________
conv_pw_6_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_6_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_7 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_7_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_7_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_7 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_7_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_7_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_8 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_8_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_8_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_8 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_8_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_8_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_9 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_9_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_9_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_9 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_9_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_9_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_10 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_10_bn (BatchNormaliz (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_10_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_10 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_10_bn (BatchNormaliz (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_10_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_11 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_11_bn (BatchNormaliz (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_11_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_11 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_11_bn (BatchNormaliz (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_11_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pad_12 (ZeroPadding2D) (None, 15, 15, 512) 0
_________________________________________________________________
conv_dw_12 (DepthwiseConv2D) (None, 7, 7, 512) 4608
_________________________________________________________________
conv_dw_12_bn (BatchNormaliz (None, 7, 7, 512) 2048
_________________________________________________________________
conv_dw_12_relu (ReLU) (None, 7, 7, 512) 0
_________________________________________________________________
conv_pw_12 (Conv2D) (None, 7, 7, 1024) 524288
_________________________________________________________________
conv_pw_12_bn (BatchNormaliz (None, 7, 7, 1024) 4096
_________________________________________________________________
conv_pw_12_relu (ReLU) (None, 7, 7, 1024) 0
_________________________________________________________________
conv_dw_13 (DepthwiseConv2D) (None, 7, 7, 1024) 9216
_________________________________________________________________
conv_dw_13_bn (BatchNormaliz (None, 7, 7, 1024) 4096
_________________________________________________________________
conv_dw_13_relu (ReLU) (None, 7, 7, 1024) 0
_________________________________________________________________
conv_pw_13 (Conv2D) (None, 7, 7, 1024) 1048576
_________________________________________________________________
conv_pw_13_bn (BatchNormaliz (None, 7, 7, 1024) 4096
_________________________________________________________________
conv_pw_13_relu (ReLU) (None, 7, 7, 1024) 0
_________________________________________________________________
global_average_pooling2d_1 ( (None, 1024) 0
_________________________________________________________________
reshape_1 (Reshape) (None, 1, 1, 1024) 0
_________________________________________________________________
dropout (Dropout) (None, 1, 1, 1024) 0
_________________________________________________________________
conv_preds (Conv2D) (None, 1, 1, 1000) 1025000
_________________________________________________________________
reshape_2 (Reshape) (None, 1000) 0
_________________________________________________________________
act_softmax (Activation) (None, 1000) 0
=================================================================
Total params: 4,253,864
Trainable params: 4,231,976
Non-trainable params: 21,888
_________________________________________________________________
Model: "model_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 224, 224, 3) 0
_________________________________________________________________
conv1_pad (ZeroPadding2D) (None, 225, 225, 3) 0
_________________________________________________________________
conv1 (Conv2D) (None, 112, 112, 32) 864
_________________________________________________________________
conv1_bn (BatchNormalization (None, 112, 112, 32) 128
_________________________________________________________________
conv1_relu (ReLU) (None, 112, 112, 32) 0
_________________________________________________________________
conv_dw_1 (DepthwiseConv2D) (None, 112, 112, 32) 288
_________________________________________________________________
conv_dw_1_bn (BatchNormaliza (None, 112, 112, 32) 128
_________________________________________________________________
conv_dw_1_relu (ReLU) (None, 112, 112, 32) 0
_________________________________________________________________
conv_pw_1 (Conv2D) (None, 112, 112, 64) 2048
_________________________________________________________________
conv_pw_1_bn (BatchNormaliza (None, 112, 112, 64) 256
_________________________________________________________________
conv_pw_1_relu (ReLU) (None, 112, 112, 64) 0
_________________________________________________________________
conv_pad_2 (ZeroPadding2D) (None, 113, 113, 64) 0
_________________________________________________________________
conv_dw_2 (DepthwiseConv2D) (None, 56, 56, 64) 576
_________________________________________________________________
conv_dw_2_bn (BatchNormaliza (None, 56, 56, 64) 256
_________________________________________________________________
conv_dw_2_relu (ReLU) (None, 56, 56, 64) 0
_________________________________________________________________
conv_pw_2 (Conv2D) (None, 56, 56, 128) 8192
_________________________________________________________________
conv_pw_2_bn (BatchNormaliza (None, 56, 56, 128) 512
_________________________________________________________________
conv_pw_2_relu (ReLU) (None, 56, 56, 128) 0
_________________________________________________________________
conv_dw_3 (DepthwiseConv2D) (None, 56, 56, 128) 1152
_________________________________________________________________
conv_dw_3_bn (BatchNormaliza (None, 56, 56, 128) 512
_________________________________________________________________
conv_dw_3_relu (ReLU) (None, 56, 56, 128) 0
_________________________________________________________________
conv_pw_3 (Conv2D) (None, 56, 56, 128) 16384
_________________________________________________________________
conv_pw_3_bn (BatchNormaliza (None, 56, 56, 128) 512
_________________________________________________________________
conv_pw_3_relu (ReLU) (None, 56, 56, 128) 0
_________________________________________________________________
conv_pad_4 (ZeroPadding2D) (None, 57, 57, 128) 0
_________________________________________________________________
conv_dw_4 (DepthwiseConv2D) (None, 28, 28, 128) 1152
_________________________________________________________________
conv_dw_4_bn (BatchNormaliza (None, 28, 28, 128) 512
_________________________________________________________________
conv_dw_4_relu (ReLU) (None, 28, 28, 128) 0
_________________________________________________________________
conv_pw_4 (Conv2D) (None, 28, 28, 256) 32768
_________________________________________________________________
conv_pw_4_bn (BatchNormaliza (None, 28, 28, 256) 1024
_________________________________________________________________
conv_pw_4_relu (ReLU) (None, 28, 28, 256) 0
_________________________________________________________________
conv_dw_5 (DepthwiseConv2D) (None, 28, 28, 256) 2304
_________________________________________________________________
conv_dw_5_bn (BatchNormaliza (None, 28, 28, 256) 1024
_________________________________________________________________
conv_dw_5_relu (ReLU) (None, 28, 28, 256) 0
_________________________________________________________________
conv_pw_5 (Conv2D) (None, 28, 28, 256) 65536
_________________________________________________________________
conv_pw_5_bn (BatchNormaliza (None, 28, 28, 256) 1024
_________________________________________________________________
conv_pw_5_relu (ReLU) (None, 28, 28, 256) 0
_________________________________________________________________
conv_pad_6 (ZeroPadding2D) (None, 29, 29, 256) 0
_________________________________________________________________
conv_dw_6 (DepthwiseConv2D) (None, 14, 14, 256) 2304
_________________________________________________________________
conv_dw_6_bn (BatchNormaliza (None, 14, 14, 256) 1024
_________________________________________________________________
conv_dw_6_relu (ReLU) (None, 14, 14, 256) 0
_________________________________________________________________
conv_pw_6 (Conv2D) (None, 14, 14, 512) 131072
_________________________________________________________________
conv_pw_6_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_6_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_7 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_7_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_7_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_7 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_7_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_7_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_8 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_8_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_8_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_8 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_8_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_8_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_9 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_9_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_9_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_9 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_9_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_9_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_10 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_10_bn (BatchNormaliz (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_10_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_10 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_10_bn (BatchNormaliz (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_10_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_11 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_11_bn (BatchNormaliz (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_11_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_11 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_11_bn (BatchNormaliz (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_11_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pad_12 (ZeroPadding2D) (None, 15, 15, 512) 0
_________________________________________________________________
conv_dw_12 (DepthwiseConv2D) (None, 7, 7, 512) 4608
_________________________________________________________________
conv_dw_12_bn (BatchNormaliz (None, 7, 7, 512) 2048
_________________________________________________________________
conv_dw_12_relu (ReLU) (None, 7, 7, 512) 0
_________________________________________________________________
conv_pw_12 (Conv2D) (None, 7, 7, 1024) 524288
_________________________________________________________________
conv_pw_12_bn (BatchNormaliz (None, 7, 7, 1024) 4096
_________________________________________________________________
conv_pw_12_relu (ReLU) (None, 7, 7, 1024) 0
_________________________________________________________________
conv_dw_13 (DepthwiseConv2D) (None, 7, 7, 1024) 9216
_________________________________________________________________
conv_dw_13_bn (BatchNormaliz (None, 7, 7, 1024) 4096
_________________________________________________________________
conv_dw_13_relu (ReLU) (None, 7, 7, 1024) 0
_________________________________________________________________
conv_pw_13 (Conv2D) (None, 7, 7, 1024) 1048576
_________________________________________________________________
conv_pw_13_bn (BatchNormaliz (None, 7, 7, 1024) 4096
_________________________________________________________________
conv_pw_13_relu (ReLU) (None, 7, 7, 1024) 0
_________________________________________________________________
global_average_pooling2d_1 ( (None, 1024) 0
_________________________________________________________________
dropout_1 (Dropout) (None, 1024) 0
_________________________________________________________________
dense_1 (Dense) (None, 7) 7175
=================================================================
Total params: 3,236,039
Trainable params: 3,214,151
Non-trainable params: 21,888
_________________________________________________________________
Epoch 1/30
Traceback (most recent call last):
File "e:/PROJECTS/PYTHON/Diabetic_Retinopathy_Detection/Deep_Learning/Code_FINAL/MobileNet_based/code/model.py", line 123, in <module>
callbacks=callbacks_list)
File "C:\Users\Prashant\Anaconda3\envs\gputest\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "C:\Users\Prashant\Anaconda3\envs\gputest\lib\site-packages\keras\engine\training.py", line 1732, in fit_generator
initial_epoch=initial_epoch)
File "C:\Users\Prashant\Anaconda3\envs\gputest\lib\site-packages\keras\engine\training_generator.py", line 220, in fit_generator
(gputest) E:\PROJECTS\PYTHON\Diabetic_Retinopathy_Detection\Deep_Learning\Code_FINAL\MobileNet_based\code>C:/Users/Prashant/Anaconda3/envs/gputest/python.exe e:/PROJECTS/PYTHON/Diabetic_Retinopathy_Detection/Deep_Learning/Code_FINAL/MobileNet_based/code/model.py
Using TensorFlow backend.
2019-12-03 00:07:35.780442: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll
2019-12-03 00:07:38.043197: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library nvcuda.dll
2019-12-03 00:07:38.065422: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
name: GeForce GTX 1060 6GB major: 6 minor: 1 memoryClockRate(GHz): 1.7085
pciBusID: 0000:01:00.0
2019-12-03 00:07:38.071819: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check.
2019-12-03 00:07:38.076417: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2019-12-03 00:07:38.080201: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2
2019-12-03 00:07:38.089178: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
name: GeForce GTX 1060 6GB major: 6 minor: 1 memoryClockRate(GHz): 1.7085
pciBusID: 0000:01:00.0
2019-12-03 00:07:38.099221: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check.
2019-12-03 00:07:38.103069: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2019-12-03 00:07:38.549799: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-12-03 00:07:38.555179: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0
2019-12-03 00:07:38.557571: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N
2019-12-03 00:07:38.560402: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4708 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060 6GB, pci bus id: 0000:01:00.0, compute capability: 6.1)
Found 31563 images belonging to 5 classes.
Found 3507 images belonging to 5 classes.
Found 3507 images belonging to 5 classes.
Model: "mobilenet_1.00_224"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 224, 224, 3) 0
_________________________________________________________________
conv1_pad (ZeroPadding2D) (None, 225, 225, 3) 0
_________________________________________________________________
conv1 (Conv2D) (None, 112, 112, 32) 864
_________________________________________________________________
conv1_bn (BatchNormalization (None, 112, 112, 32) 128
_________________________________________________________________
conv1_relu (ReLU) (None, 112, 112, 32) 0
_________________________________________________________________
conv_dw_1 (DepthwiseConv2D) (None, 112, 112, 32) 288
_________________________________________________________________
conv_dw_1_bn (BatchNormaliza (None, 112, 112, 32) 128
_________________________________________________________________
conv_dw_1_relu (ReLU) (None, 112, 112, 32) 0
_________________________________________________________________
conv_pw_1 (Conv2D) (None, 112, 112, 64) 2048
_________________________________________________________________
conv_pw_1_bn (BatchNormaliza (None, 112, 112, 64) 256
_________________________________________________________________
conv_pw_1_relu (ReLU) (None, 112, 112, 64) 0
_________________________________________________________________
conv_pad_2 (ZeroPadding2D) (None, 113, 113, 64) 0
_________________________________________________________________
conv_dw_2 (DepthwiseConv2D) (None, 56, 56, 64) 576
_________________________________________________________________
conv_dw_2_bn (BatchNormaliza (None, 56, 56, 64) 256
_________________________________________________________________
conv_dw_2_relu (ReLU) (None, 56, 56, 64) 0
_________________________________________________________________
conv_pw_2 (Conv2D) (None, 56, 56, 128) 8192
_________________________________________________________________
conv_pw_2_bn (BatchNormaliza (None, 56, 56, 128) 512
_________________________________________________________________
conv_pw_2_relu (ReLU) (None, 56, 56, 128) 0
_________________________________________________________________
conv_dw_3 (DepthwiseConv2D) (None, 56, 56, 128) 1152
_________________________________________________________________
conv_dw_3_bn (BatchNormaliza (None, 56, 56, 128) 512
_________________________________________________________________
conv_dw_3_relu (ReLU) (None, 56, 56, 128) 0
_________________________________________________________________
conv_pw_3 (Conv2D) (None, 56, 56, 128) 16384
_________________________________________________________________
conv_pw_3_bn (BatchNormaliza (None, 56, 56, 128) 512
_________________________________________________________________
conv_pw_3_relu (ReLU) (None, 56, 56, 128) 0
_________________________________________________________________
conv_pad_4 (ZeroPadding2D) (None, 57, 57, 128) 0
_________________________________________________________________
conv_dw_4 (DepthwiseConv2D) (None, 28, 28, 128) 1152
_________________________________________________________________
conv_dw_4_bn (BatchNormaliza (None, 28, 28, 128) 512
_________________________________________________________________
conv_dw_4_relu (ReLU) (None, 28, 28, 128) 0
_________________________________________________________________
conv_pw_4 (Conv2D) (None, 28, 28, 256) 32768
_________________________________________________________________
conv_pw_4_bn (BatchNormaliza (None, 28, 28, 256) 1024
_________________________________________________________________
conv_pw_4_relu (ReLU) (None, 28, 28, 256) 0
_________________________________________________________________
conv_dw_5 (DepthwiseConv2D) (None, 28, 28, 256) 2304
_________________________________________________________________
conv_dw_5_bn (BatchNormaliza (None, 28, 28, 256) 1024
_________________________________________________________________
conv_dw_5_relu (ReLU) (None, 28, 28, 256) 0
_________________________________________________________________
conv_pw_5 (Conv2D) (None, 28, 28, 256) 65536
_________________________________________________________________
conv_pw_5_bn (BatchNormaliza (None, 28, 28, 256) 1024
_________________________________________________________________
conv_pw_5_relu (ReLU) (None, 28, 28, 256) 0
_________________________________________________________________
conv_pad_6 (ZeroPadding2D) (None, 29, 29, 256) 0
_________________________________________________________________
conv_dw_6 (DepthwiseConv2D) (None, 14, 14, 256) 2304
_________________________________________________________________
conv_dw_6_bn (BatchNormaliza (None, 14, 14, 256) 1024
_________________________________________________________________
conv_dw_6_relu (ReLU) (None, 14, 14, 256) 0
_________________________________________________________________
conv_pw_6 (Conv2D) (None, 14, 14, 512) 131072
_________________________________________________________________
conv_pw_6_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_6_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_7 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_7_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_7_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_7 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_7_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_7_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_8 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_8_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_8_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_8 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_8_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_8_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_9 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_9_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_9_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_9 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_9_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_9_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_10 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_10_bn (BatchNormaliz (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_10_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_10 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_10_bn (BatchNormaliz (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_10_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_11 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_11_bn (BatchNormaliz (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_11_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_11 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_11_bn (BatchNormaliz (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_11_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pad_12 (ZeroPadding2D) (None, 15, 15, 512) 0
_________________________________________________________________
conv_dw_12 (DepthwiseConv2D) (None, 7, 7, 512) 4608
_________________________________________________________________
conv_dw_12_bn (BatchNormaliz (None, 7, 7, 512) 2048
_________________________________________________________________
conv_dw_12_relu (ReLU) (None, 7, 7, 512) 0
_________________________________________________________________
conv_pw_12 (Conv2D) (None, 7, 7, 1024) 524288
_________________________________________________________________
conv_pw_12_bn (BatchNormaliz (None, 7, 7, 1024) 4096
_________________________________________________________________
conv_pw_12_relu (ReLU) (None, 7, 7, 1024) 0
_________________________________________________________________
conv_dw_13 (DepthwiseConv2D) (None, 7, 7, 1024) 9216
_________________________________________________________________
conv_dw_13_bn (BatchNormaliz (None, 7, 7, 1024) 4096
_________________________________________________________________
conv_dw_13_relu (ReLU) (None, 7, 7, 1024) 0
_________________________________________________________________
conv_pw_13 (Conv2D) (None, 7, 7, 1024) 1048576
_________________________________________________________________
conv_pw_13_bn (BatchNormaliz (None, 7, 7, 1024) 4096
_________________________________________________________________
conv_pw_13_relu (ReLU) (None, 7, 7, 1024) 0
_________________________________________________________________
global_average_pooling2d_1 ( (None, 1024) 0
_________________________________________________________________
reshape_1 (Reshape) (None, 1, 1, 1024) 0
_________________________________________________________________
dropout (Dropout) (None, 1, 1, 1024) 0
_________________________________________________________________
conv_preds (Conv2D) (None, 1, 1, 1000) 1025000
_________________________________________________________________
reshape_2 (Reshape) (None, 1000) 0
_________________________________________________________________
act_softmax (Activation) (None, 1000) 0
=================================================================
Total params: 4,253,864
Trainable params: 4,231,976
Non-trainable params: 21,888
_________________________________________________________________
Model: "model_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 224, 224, 3) 0
_________________________________________________________________
conv1_pad (ZeroPadding2D) (None, 225, 225, 3) 0
_________________________________________________________________
conv1 (Conv2D) (None, 112, 112, 32) 864
_________________________________________________________________
conv1_bn (BatchNormalization (None, 112, 112, 32) 128
_________________________________________________________________
conv1_relu (ReLU) (None, 112, 112, 32) 0
_________________________________________________________________
conv_dw_1 (DepthwiseConv2D) (None, 112, 112, 32) 288
_________________________________________________________________
conv_dw_1_bn (BatchNormaliza (None, 112, 112, 32) 128
_________________________________________________________________
conv_dw_1_relu (ReLU) (None, 112, 112, 32) 0
_________________________________________________________________
conv_pw_1 (Conv2D) (None, 112, 112, 64) 2048
_________________________________________________________________
conv_pw_1_bn (BatchNormaliza (None, 112, 112, 64) 256
_________________________________________________________________
conv_pw_1_relu (ReLU) (None, 112, 112, 64) 0
_________________________________________________________________
conv_pad_2 (ZeroPadding2D) (None, 113, 113, 64) 0
_________________________________________________________________
conv_dw_2 (DepthwiseConv2D) (None, 56, 56, 64) 576
_________________________________________________________________
conv_dw_2_bn (BatchNormaliza (None, 56, 56, 64) 256
_________________________________________________________________
conv_dw_2_relu (ReLU) (None, 56, 56, 64) 0
_________________________________________________________________
conv_pw_2 (Conv2D) (None, 56, 56, 128) 8192
_________________________________________________________________
conv_pw_2_bn (BatchNormaliza (None, 56, 56, 128) 512
_________________________________________________________________
conv_pw_2_relu (ReLU) (None, 56, 56, 128) 0
_________________________________________________________________
conv_dw_3 (DepthwiseConv2D) (None, 56, 56, 128) 1152
_________________________________________________________________
conv_dw_3_bn (BatchNormaliza (None, 56, 56, 128) 512
_________________________________________________________________
conv_dw_3_relu (ReLU) (None, 56, 56, 128) 0
_________________________________________________________________
conv_pw_3 (Conv2D) (None, 56, 56, 128) 16384
_________________________________________________________________
conv_pw_3_bn (BatchNormaliza (None, 56, 56, 128) 512
_________________________________________________________________
conv_pw_3_relu (ReLU) (None, 56, 56, 128) 0
_________________________________________________________________
conv_pad_4 (ZeroPadding2D) (None, 57, 57, 128) 0
_________________________________________________________________
conv_dw_4 (DepthwiseConv2D) (None, 28, 28, 128) 1152
_________________________________________________________________
conv_dw_4_bn (BatchNormaliza (None, 28, 28, 128) 512
_________________________________________________________________
conv_dw_4_relu (ReLU) (None, 28, 28, 128) 0
_________________________________________________________________
conv_pw_4 (Conv2D) (None, 28, 28, 256) 32768
_________________________________________________________________
conv_pw_4_bn (BatchNormaliza (None, 28, 28, 256) 1024
_________________________________________________________________
conv_pw_4_relu (ReLU) (None, 28, 28, 256) 0
_________________________________________________________________
conv_dw_5 (DepthwiseConv2D) (None, 28, 28, 256) 2304
_________________________________________________________________
conv_dw_5_bn (BatchNormaliza (None, 28, 28, 256) 1024
_________________________________________________________________
conv_dw_5_relu (ReLU) (None, 28, 28, 256) 0
_________________________________________________________________
conv_pw_5 (Conv2D) (None, 28, 28, 256) 65536
_________________________________________________________________
conv_pw_5_bn (BatchNormaliza (None, 28, 28, 256) 1024
_________________________________________________________________
conv_pw_5_relu (ReLU) (None, 28, 28, 256) 0
_________________________________________________________________
conv_pad_6 (ZeroPadding2D) (None, 29, 29, 256) 0
_________________________________________________________________
conv_dw_6 (DepthwiseConv2D) (None, 14, 14, 256) 2304
_________________________________________________________________
conv_dw_6_bn (BatchNormaliza (None, 14, 14, 256) 1024
_________________________________________________________________
conv_dw_6_relu (ReLU) (None, 14, 14, 256) 0
_________________________________________________________________
conv_pw_6 (Conv2D) (None, 14, 14, 512) 131072
_________________________________________________________________
conv_pw_6_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_6_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_7 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_7_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_7_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_7 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_7_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_7_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_8 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_8_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_8_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_8 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_8_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_8_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_9 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_9_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_9_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_9 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_9_bn (BatchNormaliza (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_9_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_10 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_10_bn (BatchNormaliz (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_10_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_10 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_10_bn (BatchNormaliz (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_10_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_dw_11 (DepthwiseConv2D) (None, 14, 14, 512) 4608
_________________________________________________________________
conv_dw_11_bn (BatchNormaliz (None, 14, 14, 512) 2048
_________________________________________________________________
conv_dw_11_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pw_11 (Conv2D) (None, 14, 14, 512) 262144
_________________________________________________________________
conv_pw_11_bn (BatchNormaliz (None, 14, 14, 512) 2048
_________________________________________________________________
conv_pw_11_relu (ReLU) (None, 14, 14, 512) 0
_________________________________________________________________
conv_pad_12 (ZeroPadding2D) (None, 15, 15, 512) 0
_________________________________________________________________
conv_dw_12 (DepthwiseConv2D) (None, 7, 7, 512) 4608
_________________________________________________________________
conv_dw_12_bn (BatchNormaliz (None, 7, 7, 512) 2048
_________________________________________________________________
conv_dw_12_relu (ReLU) (None, 7, 7, 512) 0
_________________________________________________________________
conv_pw_12 (Conv2D) (None, 7, 7, 1024) 524288
_________________________________________________________________
conv_pw_12_bn (BatchNormaliz (None, 7, 7, 1024) 4096
_________________________________________________________________
conv_pw_12_relu (ReLU) (None, 7, 7, 1024) 0
_________________________________________________________________
conv_dw_13 (DepthwiseConv2D) (None, 7, 7, 1024) 9216
_________________________________________________________________
conv_dw_13_bn (BatchNormaliz (None, 7, 7, 1024) 4096
_________________________________________________________________
conv_dw_13_relu (ReLU) (None, 7, 7, 1024) 0
_________________________________________________________________
conv_pw_13 (Conv2D) (None, 7, 7, 1024) 1048576
_________________________________________________________________
conv_pw_13_bn (BatchNormaliz (None, 7, 7, 1024) 4096
_________________________________________________________________
conv_pw_13_relu (ReLU) (None, 7, 7, 1024) 0
_________________________________________________________________
global_average_pooling2d_1 ( (None, 1024) 0
_________________________________________________________________
dropout_1 (Dropout) (None, 1024) 0
_________________________________________________________________
dense_1 (Dense) (None, 5) 5125
=================================================================
Total params: 3,233,989
Trainable params: 3,212,101
Non-trainable params: 21,888
_________________________________________________________________
Epoch 1/30
2019-12-03 00:07:49.335131: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll
2019-12-03 00:07:50.092857: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2019-12-03 00:07:51.935489: W tensorflow/stream_executor/cuda/redzone_allocator.cc:312] Internal: Invoking ptxas not supported on Windows
Relying on driver to perform ptx compilation. This message will be only logged once.
3157/3157 [==============================] - 240s 76ms/step - loss: 5.6897 - categorical_accuracy: 0.3148 - top_2_accuracy: 0.6156 - top_3_accuracy: 0.8129 - val_loss: 1.9570 - val_categorical_accuracy: 0.0696 - val_top_2_accuracy: 0.7887 - val_top_3_accuracy: 0.9290
Epoch 00001: val_top_3_accuracy improved from -inf to 0.92900, saving model to model.h5
Epoch 2/30
3157/3157 [==============================] - 233s 74ms/step - loss: 5.3744 - categorical_accuracy: 0.3211 - top_2_accuracy: 0.6447 - top_3_accuracy: 0.8389 - val_loss: 1.8537 - val_categorical_accuracy: 0.3151 - val_top_2_accuracy: 0.7984 - val_top_3_accuracy: 0.9156
Epoch 00002: val_top_3_accuracy did not improve from 0.92900
Epoch 3/30
3157/3157 [==============================] - 236s 75ms/step - loss: 5.3726 - categorical_accuracy: 0.3314 - top_2_accuracy: 0.6497 - top_3_accuracy: 0.8496 - val_loss: 5.9991 - val_categorical_accuracy: 0.1514 - val_top_2_accuracy: 0.7066 - val_top_3_accuracy: 0.8777
Epoch 00003: val_top_3_accuracy did not improve from 0.92900
Epoch 00003: ReduceLROnPlateau reducing learning rate to 0.004999999888241291.
Epoch 4/30
3157/3157 [==============================] - 235s 74ms/step - loss: 4.7312 - categorical_accuracy: 0.3503 - top_2_accuracy: 0.6890 - top_3_accuracy: 0.8711 - val_loss: 1.1794 - val_categorical_accuracy: 0.7180 - val_top_2_accuracy: 0.8474 - val_top_3_accuracy: 0.9581
Epoch 00004: val_top_3_accuracy improved from 0.92900 to 0.95808, saving model to model.h5
Epoch 5/30
3157/3157 [==============================] - 233s 74ms/step - loss: 4.4956 - categorical_accuracy: 0.3603 - top_2_accuracy: 0.7073 - top_3_accuracy: 0.8876 - val_loss: 1.1080 - val_categorical_accuracy: 0.4405 - val_top_2_accuracy: 0.8289 - val_top_3_accuracy: 0.9615
Epoch 00005: val_top_3_accuracy improved from 0.95808 to 0.96151, saving model to model.h5
Epoch 6/30
3157/3157 [==============================] - 238s 75ms/step - loss: 4.4028 - categorical_accuracy: 0.3696 - top_2_accuracy: 0.7182 - top_3_accuracy: 0.8926 - val_loss: 1.3949 - val_categorical_accuracy: 0.4996 - val_top_2_accuracy: 0.8090 - val_top_3_accuracy: 0.9589
Epoch 00006: val_top_3_accuracy did not improve from 0.96151
Epoch 7/30
3157/3157 [==============================] - 235s 74ms/step - loss: 4.2200 - categorical_accuracy: 0.3806 - top_2_accuracy: 0.7263 - top_3_accuracy: 0.9034 - val_loss: 1.3652 - val_categorical_accuracy: 0.0978 - val_top_2_accuracy: 0.7810 - val_top_3_accuracy: 0.9572
Epoch 00007: val_top_3_accuracy did not improve from 0.96151
Epoch 00007: ReduceLROnPlateau reducing learning rate to 0.0024999999441206455.
Epoch 8/30
3157/3157 [==============================] - 232s 74ms/step - loss: 3.7653 - categorical_accuracy: 0.3948 - top_2_accuracy: 0.7617 - top_3_accuracy: 0.9231 - val_loss: 0.7869 - val_categorical_accuracy: 0.6453 - val_top_2_accuracy: 0.8107 - val_top_3_accuracy: 0.9589
Epoch 00008: val_top_3_accuracy did not improve from 0.96151
Epoch 9/30
3157/3157 [==============================] - 232s 73ms/step - loss: 3.5360 - categorical_accuracy: 0.4035 - top_2_accuracy: 0.7655 - top_3_accuracy: 0.9354 - val_loss: 0.7615 - val_categorical_accuracy: 0.6248 - val_top_2_accuracy: 0.8135 - val_top_3_accuracy: 0.9618
Epoch 00009: val_top_3_accuracy improved from 0.96151 to 0.96179, saving model to model.h5
Epoch 10/30
3157/3157 [==============================] - 229s 73ms/step - loss: 3.3796 - categorical_accuracy: 0.4070 - top_2_accuracy: 0.7795 - top_3_accuracy: 0.9463 - val_loss: 0.9581 - val_categorical_accuracy: 0.2161 - val_top_2_accuracy: 0.8115 - val_top_3_accuracy: 0.9578
Epoch 00010: val_top_3_accuracy did not improve from 0.96179
Epoch 11/30
3157/3157 [==============================] - 232s 73ms/step - loss: 3.1816 - categorical_accuracy: 0.4110 - top_2_accuracy: 0.7876 - top_3_accuracy: 0.9550 - val_loss: 1.6400 - val_categorical_accuracy: 0.4500 - val_top_2_accuracy: 0.8135 - val_top_3_accuracy: 0.9598
Epoch 00011: val_top_3_accuracy did not improve from 0.96179
Epoch 00011: ReduceLROnPlateau reducing learning rate to 0.0012499999720603228.
Epoch 12/30
3157/3157 [==============================] - 233s 74ms/step - loss: 2.8703 - categorical_accuracy: 0.4294 - top_2_accuracy: 0.8124 - top_3_accuracy: 0.9708 - val_loss: 1.1546 - val_categorical_accuracy: 0.7149 - val_top_2_accuracy: 0.8172 - val_top_3_accuracy: 0.9615
Epoch 00012: val_top_3_accuracy did not improve from 0.96179
Epoch 13/30
3157/3157 [==============================] - 230s 73ms/step - loss: 2.8148 - categorical_accuracy: 0.4439 - top_2_accuracy: 0.8198 - top_3_accuracy: 0.9744 - val_loss: 0.5940 - val_categorical_accuracy: 0.4582 - val_top_2_accuracy: 0.8181 - val_top_3_accuracy: 0.9641
Epoch 00013: val_top_3_accuracy improved from 0.96179 to 0.96407, saving model to model.h5
Epoch 14/30
3157/3157 [==============================] - 230s 73ms/step - loss: 2.6545 - categorical_accuracy: 0.4573 - top_2_accuracy: 0.8340 - top_3_accuracy: 0.9818 - val_loss: 0.8637 - val_categorical_accuracy: 0.5284 - val_top_2_accuracy: 0.8195 - val_top_3_accuracy: 0.9624
Epoch 00014: val_top_3_accuracy did not improve from 0.96407
Epoch 15/30
3157/3157 [==============================] - 232s 73ms/step - loss: 2.5966 - categorical_accuracy: 0.4576 - top_2_accuracy: 0.8386 - top_3_accuracy: 0.9829 - val_loss: 1.3761 - val_categorical_accuracy: 0.6319 - val_top_2_accuracy: 0.8184 - val_top_3_accuracy: 0.9615
Epoch 00015: val_top_3_accuracy did not improve from 0.96407
Epoch 00015: ReduceLROnPlateau reducing learning rate to 0.0006249999860301614.
Epoch 16/30
3157/3157 [==============================] - 232s 74ms/step - loss: 2.4249 - categorical_accuracy: 0.4729 - top_2_accuracy: 0.8443 - top_3_accuracy: 0.9864 - val_loss: 2.8359 - val_categorical_accuracy: 0.5985 - val_top_2_accuracy: 0.8172 - val_top_3_accuracy: 0.9618
Epoch 00016: val_top_3_accuracy did not improve from 0.96407
Epoch 17/30
3157/3157 [==============================] - 234s 74ms/step - loss: 2.3690 - categorical_accuracy: 0.4854 - top_2_accuracy: 0.8570 - top_3_accuracy: 0.9888 - val_loss: 0.5132 - val_categorical_accuracy: 0.6886 - val_top_2_accuracy: 0.8181 - val_top_3_accuracy: 0.9618
Epoch 00017: val_top_3_accuracy did not improve from 0.96407
Epoch 00017: ReduceLROnPlateau reducing learning rate to 0.0003124999930150807.
Epoch 18/30
3157/3157 [==============================] - 232s 74ms/step - loss: 2.2893 - categorical_accuracy: 0.5032 - top_2_accuracy: 0.8616 - top_3_accuracy: 0.9899 - val_loss: 2.1007 - val_categorical_accuracy: 0.5823 - val_top_2_accuracy: 0.8201 - val_top_3_accuracy: 0.9615
Epoch 00018: val_top_3_accuracy did not improve from 0.96407
Epoch 19/30
3157/3157 [==============================] - 233s 74ms/step - loss: 2.2395 - categorical_accuracy: 0.4991 - top_2_accuracy: 0.8658 - top_3_accuracy: 0.9923 - val_loss: 0.8153 - val_categorical_accuracy: 0.5666 - val_top_2_accuracy: 0.8169 - val_top_3_accuracy: 0.9621
Epoch 00019: val_top_3_accuracy did not improve from 0.96407
Epoch 00019: ReduceLROnPlateau reducing learning rate to 0.00015624999650754035.
Epoch 20/30
3157/3157 [==============================] - 233s 74ms/step - loss: 2.2058 - categorical_accuracy: 0.5178 - top_2_accuracy: 0.8706 - top_3_accuracy: 0.9920 - val_loss: 3.2544 - val_categorical_accuracy: 0.6362 - val_top_2_accuracy: 0.8209 - val_top_3_accuracy: 0.9621
Epoch 00020: val_top_3_accuracy did not improve from 0.96407
Epoch 21/30
3157/3157 [==============================] - 235s 75ms/step - loss: 2.2087 - categorical_accuracy: 0.5101 - top_2_accuracy: 0.8679 - top_3_accuracy: 0.9922 - val_loss: 1.0586 - val_categorical_accuracy: 0.6113 - val_top_2_accuracy: 0.8195 - val_top_3_accuracy: 0.9624
Epoch 00021: val_top_3_accuracy did not improve from 0.96407
Epoch 00021: ReduceLROnPlateau reducing learning rate to 7.812499825377017e-05.
Epoch 22/30
3157/3157 [==============================] - 233s 74ms/step - loss: 2.1499 - categorical_accuracy: 0.5199 - top_2_accuracy: 0.8737 - top_3_accuracy: 0.9925 - val_loss: 1.1943 - val_categorical_accuracy: 0.6065 - val_top_2_accuracy: 0.8201 - val_top_3_accuracy: 0.9621
Epoch 00022: val_top_3_accuracy did not improve from 0.96407
Epoch 23/30
3157/3157 [==============================] - 233s 74ms/step - loss: 2.1309 - categorical_accuracy: 0.5250 - top_2_accuracy: 0.8793 - top_3_accuracy: 0.9940 - val_loss: 1.4897 - val_categorical_accuracy: 0.5851 - val_top_2_accuracy: 0.8198 - val_top_3_accuracy: 0.9621
Epoch 00023: val_top_3_accuracy did not improve from 0.96407
Epoch 00023: ReduceLROnPlateau reducing learning rate to 3.9062499126885086e-05.
Epoch 24/30
3157/3157 [==============================] - 231s 73ms/step - loss: 2.1241 - categorical_accuracy: 0.5216 - top_2_accuracy: 0.8789 - top_3_accuracy: 0.9939 - val_loss: 1.2535 - val_categorical_accuracy: 0.5654 - val_top_2_accuracy: 0.8189 - val_top_3_accuracy: 0.9624
Epoch 00024: val_top_3_accuracy did not improve from 0.96407
Epoch 25/30
3157/3157 [==============================] - 230s 73ms/step - loss: 2.1401 - categorical_accuracy: 0.5243 - top_2_accuracy: 0.8801 - top_3_accuracy: 0.9944 - val_loss: 1.2436 - val_categorical_accuracy: 0.5555 - val_top_2_accuracy: 0.8186 - val_top_3_accuracy: 0.9624
Epoch 00025: val_top_3_accuracy did not improve from 0.96407
Epoch 00025: ReduceLROnPlateau reducing learning rate to 1.9531249563442543e-05.
Epoch 26/30
3157/3157 [==============================] - 234s 74ms/step - loss: 2.1246 - categorical_accuracy: 0.5146 - top_2_accuracy: 0.8765 - top_3_accuracy: 0.9931 - val_loss: 1.1337 - val_categorical_accuracy: 0.5751 - val_top_2_accuracy: 0.8184 - val_top_3_accuracy: 0.9624
Epoch 00026: val_top_3_accuracy did not improve from 0.96407
Epoch 27/30
3157/3157 [==============================] - 231s 73ms/step - loss: 2.0866 - categorical_accuracy: 0.5270 - top_2_accuracy: 0.8809 - top_3_accuracy: 0.9943 - val_loss: 0.7890 - val_categorical_accuracy: 0.5560 - val_top_2_accuracy: 0.8184 - val_top_3_accuracy: 0.9624
Epoch 00027: val_top_3_accuracy did not improve from 0.96407
Epoch 00027: ReduceLROnPlateau reducing learning rate to 1e-05.
Epoch 28/30
3157/3157 [==============================] - 234s 74ms/step - loss: 2.0882 - categorical_accuracy: 0.5215 - top_2_accuracy: 0.8820 - top_3_accuracy: 0.9944 - val_loss: 0.5893 - val_categorical_accuracy: 0.5771 - val_top_2_accuracy: 0.8201 - val_top_3_accuracy: 0.9621
Epoch 00028: val_top_3_accuracy did not improve from 0.96407
Epoch 29/30
3157/3157 [==============================] - 233s 74ms/step - loss: 2.1091 - categorical_accuracy: 0.5280 - top_2_accuracy: 0.8824 - top_3_accuracy: 0.9944 - val_loss: 0.4859 - val_categorical_accuracy: 0.5834 - val_top_2_accuracy: 0.8201 - val_top_3_accuracy: 0.9621
Epoch 00029: val_top_3_accuracy did not improve from 0.96407
Epoch 30/30
3157/3157 [==============================] - 231s 73ms/step - loss: 2.1145 - categorical_accuracy: 0.5236 - top_2_accuracy: 0.8779 - top_3_accuracy: 0.9944 - val_loss: 0.6381 - val_categorical_accuracy: 0.5880 - val_top_2_accuracy: 0.8201 - val_top_3_accuracy: 0.9624
Epoch 00030: val_top_3_accuracy did not improve from 0.96407
val_loss: 6.946740627288818
val_cat_acc: 0.5879669189453125
val_top_2_acc: 0.8200741410255432
val_top_3_acc: 0.9623609781265259
val_loss: 4.780903339385986
val_cat_acc: 0.45822641253471375
val_top_2_acc: 0.8180781006813049
val_top_3_acc: 0.9640718698501587
351/351 [==============================] - 14s 39ms/step
Confusion matrix, without normalization
[[1474 1081 8 5 10]
[ 153 89 0 0 1]
[ 276 222 20 6 5]
[ 43 29 7 8 0]
[ 24 15 10 5 16]]
Moderatörün son düzenlenenleri:
