log_train_py.txt

Using TensorFlow backend.
WARNING:tensorflow:From /usr/local/lib/python3.5/dist-packages/tensorflow/contrib/learn/python/learn/datasets/base.py:198: retry (from tensorflow.contrib.learn.python.learn.datasets.base) is deprecated and will be removed in a future version.
Instructions for updating:
Use the retry module or similar alternatives.
2018-04-25 21:27:47.392990: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2018-04-25 21:27:47.527610: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:898] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2018-04-25 21:27:47.528025: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1344] Found device 0 with properties: 
name: Quadro M500M major: 5 minor: 0 memoryClockRate(GHz): 1.124
pciBusID: 0000:06:00.0
totalMemory: 1.96GiB freeMemory: 1.55GiB
2018-04-25 21:27:47.528050: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1423] Adding visible gpu devices: 0
2018-04-25 21:27:48.118666: I tensorflow/core/common_runtime/gpu/gpu_device.cc:911] Device interconnect StreamExecutor with strength 1 edge matrix:
2018-04-25 21:27:48.118692: I tensorflow/core/common_runtime/gpu/gpu_device.cc:917]      0 
2018-04-25 21:27:48.118698: I tensorflow/core/common_runtime/gpu/gpu_device.cc:930] 0:   N 
2018-04-25 21:27:48.118852: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1041] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 1306 MB memory) -> physical GPU (device: 0, name: Quadro M500M, pci bus id: 0000:06:00.0, compute capability: 5.0)
{'dtype': 'float32', 'name': 'input_1', 'sparse': False, 'batch_input_shape': (None, None, None, 3)}
{'use_bias': True, 'activation': 'relu', 'dilation_rate': (1, 1), 'activity_regularizer': None, 'padding': 'same', 'kernel_size': (3, 3), 'filters': 64, 'kernel_regularizer': None, 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'mode': 'fan_avg', 'scale': 1.0, 'distribution': 'uniform', 'seed': None}}, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'data_format': 'channels_last', 'kernel_constraint': None, 'name': 'block1_conv1', 'bias_regularizer': None, 'strides': (1, 1), 'bias_constraint': None, 'trainable': True}
{'use_bias': True, 'activation': 'relu', 'dilation_rate': (1, 1), 'activity_regularizer': None, 'padding': 'same', 'kernel_size': (3, 3), 'filters': 64, 'kernel_regularizer': None, 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'mode': 'fan_avg', 'scale': 1.0, 'distribution': 'uniform', 'seed': None}}, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'data_format': 'channels_last', 'kernel_constraint': None, 'name': 'block1_conv2', 'bias_regularizer': None, 'strides': (1, 1), 'bias_constraint': None, 'trainable': True}
{'pool_size': (2, 2), 'padding': 'valid', 'name': 'block1_pool', 'data_format': 'channels_last', 'strides': (2, 2), 'trainable': True}
{'use_bias': True, 'activation': 'relu', 'dilation_rate': (1, 1), 'activity_regularizer': None, 'padding': 'same', 'kernel_size': (3, 3), 'filters': 128, 'kernel_regularizer': None, 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'mode': 'fan_avg', 'scale': 1.0, 'distribution': 'uniform', 'seed': None}}, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'data_format': 'channels_last', 'kernel_constraint': None, 'name': 'block2_conv1', 'bias_regularizer': None, 'strides': (1, 1), 'bias_constraint': None, 'trainable': True}
{'use_bias': True, 'activation': 'relu', 'dilation_rate': (1, 1), 'activity_regularizer': None, 'padding': 'same', 'kernel_size': (3, 3), 'filters': 128, 'kernel_regularizer': None, 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'mode': 'fan_avg', 'scale': 1.0, 'distribution': 'uniform', 'seed': None}}, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'data_format': 'channels_last', 'kernel_constraint': None, 'name': 'block2_conv2', 'bias_regularizer': None, 'strides': (1, 1), 'bias_constraint': None, 'trainable': True}
{'pool_size': (2, 2), 'padding': 'valid', 'name': 'block2_pool', 'data_format': 'channels_last', 'strides': (2, 2), 'trainable': True}
{'use_bias': True, 'activation': 'relu', 'dilation_rate': (1, 1), 'activity_regularizer': None, 'padding': 'same', 'kernel_size': (3, 3), 'filters': 256, 'kernel_regularizer': None, 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'mode': 'fan_avg', 'scale': 1.0, 'distribution': 'uniform', 'seed': None}}, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'data_format': 'channels_last', 'kernel_constraint': None, 'name': 'block3_conv1', 'bias_regularizer': None, 'strides': (1, 1), 'bias_constraint': None, 'trainable': True}
{'use_bias': True, 'activation': 'relu', 'dilation_rate': (1, 1), 'activity_regularizer': None, 'padding': 'same', 'kernel_size': (3, 3), 'filters': 256, 'kernel_regularizer': None, 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'mode': 'fan_avg', 'scale': 1.0, 'distribution': 'uniform', 'seed': None}}, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'data_format': 'channels_last', 'kernel_constraint': None, 'name': 'block3_conv2', 'bias_regularizer': None, 'strides': (1, 1), 'bias_constraint': None, 'trainable': True}
{'use_bias': True, 'activation': 'relu', 'dilation_rate': (1, 1), 'activity_regularizer': None, 'padding': 'same', 'kernel_size': (3, 3), 'filters': 256, 'kernel_regularizer': None, 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'mode': 'fan_avg', 'scale': 1.0, 'distribution': 'uniform', 'seed': None}}, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'data_format': 'channels_last', 'kernel_constraint': None, 'name': 'block3_conv3', 'bias_regularizer': None, 'strides': (1, 1), 'bias_constraint': None, 'trainable': True}
{'use_bias': True, 'activation': 'relu', 'dilation_rate': (1, 1), 'activity_regularizer': None, 'padding': 'same', 'kernel_size': (3, 3), 'filters': 256, 'kernel_regularizer': None, 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'mode': 'fan_avg', 'scale': 1.0, 'distribution': 'uniform', 'seed': None}}, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'data_format': 'channels_last', 'kernel_constraint': None, 'name': 'block3_conv4', 'bias_regularizer': None, 'strides': (1, 1), 'bias_constraint': None, 'trainable': True}
{'pool_size': (2, 2), 'padding': 'valid', 'name': 'block3_pool', 'data_format': 'channels_last', 'strides': (2, 2), 'trainable': True}
{'use_bias': True, 'activation': 'relu', 'dilation_rate': (1, 1), 'activity_regularizer': None, 'padding': 'same', 'kernel_size': (3, 3), 'filters': 512, 'kernel_regularizer': None, 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'mode': 'fan_avg', 'scale': 1.0, 'distribution': 'uniform', 'seed': None}}, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'data_format': 'channels_last', 'kernel_constraint': None, 'name': 'block4_conv1', 'bias_regularizer': None, 'strides': (1, 1), 'bias_constraint': None, 'trainable': True}
{'use_bias': True, 'activation': 'relu', 'dilation_rate': (1, 1), 'activity_regularizer': None, 'padding': 'same', 'kernel_size': (3, 3), 'filters': 512, 'kernel_regularizer': None, 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'mode': 'fan_avg', 'scale': 1.0, 'distribution': 'uniform', 'seed': None}}, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'data_format': 'channels_last', 'kernel_constraint': None, 'name': 'block4_conv2', 'bias_regularizer': None, 'strides': (1, 1), 'bias_constraint': None, 'trainable': True}
{'use_bias': True, 'activation': 'relu', 'dilation_rate': (1, 1), 'activity_regularizer': None, 'padding': 'same', 'kernel_size': (3, 3), 'filters': 512, 'kernel_regularizer': None, 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'mode': 'fan_avg', 'scale': 1.0, 'distribution': 'uniform', 'seed': None}}, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'data_format': 'channels_last', 'kernel_constraint': None, 'name': 'block4_conv3', 'bias_regularizer': None, 'strides': (1, 1), 'bias_constraint': None, 'trainable': True}
{'use_bias': True, 'activation': 'relu', 'dilation_rate': (1, 1), 'activity_regularizer': None, 'padding': 'same', 'kernel_size': (3, 3), 'filters': 512, 'kernel_regularizer': None, 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'mode': 'fan_avg', 'scale': 1.0, 'distribution': 'uniform', 'seed': None}}, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'data_format': 'channels_last', 'kernel_constraint': None, 'name': 'block4_conv4', 'bias_regularizer': None, 'strides': (1, 1), 'bias_constraint': None, 'trainable': True}
{'pool_size': (2, 2), 'padding': 'valid', 'name': 'block4_pool', 'data_format': 'channels_last', 'strides': (2, 2), 'trainable': True}
{'use_bias': True, 'activation': 'relu', 'dilation_rate': (1, 1), 'activity_regularizer': None, 'padding': 'same', 'kernel_size': (3, 3), 'filters': 512, 'kernel_regularizer': None, 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'mode': 'fan_avg', 'scale': 1.0, 'distribution': 'uniform', 'seed': None}}, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'data_format': 'channels_last', 'kernel_constraint': None, 'name': 'block5_conv1', 'bias_regularizer': None, 'strides': (1, 1), 'bias_constraint': None, 'trainable': True}
{'use_bias': True, 'activation': 'relu', 'dilation_rate': (1, 1), 'activity_regularizer': None, 'padding': 'same', 'kernel_size': (3, 3), 'filters': 512, 'kernel_regularizer': None, 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'mode': 'fan_avg', 'scale': 1.0, 'distribution': 'uniform', 'seed': None}}, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'data_format': 'channels_last', 'kernel_constraint': None, 'name': 'block5_conv2', 'bias_regularizer': None, 'strides': (1, 1), 'bias_constraint': None, 'trainable': True}
{'use_bias': True, 'activation': 'relu', 'dilation_rate': (1, 1), 'activity_regularizer': None, 'padding': 'same', 'kernel_size': (3, 3), 'filters': 512, 'kernel_regularizer': None, 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'mode': 'fan_avg', 'scale': 1.0, 'distribution': 'uniform', 'seed': None}}, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'data_format': 'channels_last', 'kernel_constraint': None, 'name': 'block5_conv3', 'bias_regularizer': None, 'strides': (1, 1), 'bias_constraint': None, 'trainable': True}
{'use_bias': True, 'activation': 'relu', 'dilation_rate': (1, 1), 'activity_regularizer': None, 'padding': 'same', 'kernel_size': (3, 3), 'filters': 512, 'kernel_regularizer': None, 'kernel_initializer': {'class_name': 'VarianceScaling', 'config': {'mode': 'fan_avg', 'scale': 1.0, 'distribution': 'uniform', 'seed': None}}, 'bias_initializer': {'class_name': 'Zeros', 'config': {}}, 'data_format': 'channels_last', 'kernel_constraint': None, 'name': 'block5_conv4', 'bias_regularizer': None, 'strides': (1, 1), 'bias_constraint': None, 'trainable': True}
{'pool_size': (2, 2), 'padding': 'valid', 'name': 'block5_pool', 'data_format': 'channels_last', 'strides': (2, 2), 'trainable': True}
{'data_format': 'channels_last', 'name': 'global_average_pooling2d_1', 'trainable': True}
Extracting images from archive...
Extraction done. It took 1.05 s.
Splitting dataset...
Split done. It took 0.32 s.
Found 1493 images belonging to 3 classes.
RGB mean values:
[111.88987243135901, 109.86521778236771, 81.55134317023249]
Found 496 images belonging to 3 classes.
Epoch 1/50
93/93 [==============================] - 143s 2s/step - loss: 0.5329 - acc: 0.8273 - val_loss: 0.3152 - val_acc: 0.9052

Epoch 00001: val_acc improved from -inf to 0.90524, saving model to data/model/keras_vgg19.h5
Epoch 2/50
93/93 [==============================] - 134s 1s/step - loss: 0.1517 - acc: 0.9488 - val_loss: 0.3133 - val_acc: 0.9133

Epoch 00002: val_acc improved from 0.90524 to 0.91331, saving model to data/model/keras_vgg19.h5
Epoch 3/50
93/93 [==============================] - 134s 1s/step - loss: 0.0758 - acc: 0.9751 - val_loss: 0.2925 - val_acc: 0.9093

Epoch 00003: val_acc did not improve
Epoch 00003: early stopping
2018-04-25 21:34:46.594165: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1423] Adding visible gpu devices: 0
2018-04-25 21:34:46.594212: I tensorflow/core/common_runtime/gpu/gpu_device.cc:911] Device interconnect StreamExecutor with strength 1 edge matrix:
2018-04-25 21:34:46.594221: I tensorflow/core/common_runtime/gpu/gpu_device.cc:917]      0 
2018-04-25 21:34:46.594229: I tensorflow/core/common_runtime/gpu/gpu_device.cc:930] 0:   N 
2018-04-25 21:34:46.594352: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1041] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 1306 MB memory) -> physical GPU (device: 0, name: Quadro M500M, pci bus id: 0000:06:00.0, compute capability: 5.0)
Converted 36 variables to const ops.