Image Dimension: 300x500

gistfile1.txt

img_width, img_height = 300, 500
*********************************************************

if K.image_data_format() == 'channels_first':
    input_shape = (3, img_width, img_height)
else:
    input_shape = (img_width, img_height, 3)


model = Sequential()
model.add(Conv2D(128, (7, 7), padding = 'same', input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))

model.add(Conv2D(128, (7, 7), padding = 'same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.6))

model.add(Conv2D(128, (7, 7), padding = 'same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.6))

model.add(Conv2D(128, (7, 7), padding = 'same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.6))

model.add(Conv2D(64, (7, 7), padding = 'same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.6))

model.add(Conv2D(64, (7, 7), padding = 'same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.6))

model.add(Conv2D(32, (7, 7), padding = 'same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.6))

model.add(Flatten())
model.add(Dense(32))
model.add(Activation('relu'))
model.add(Dense(1))
model.add(Activation('sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer=optimizers.Adam(lr=3e-5),
              metrics=['accuracy'])

model.summary()


*************************************************************************************
Found 29124 images belonging to 2 classes.
Found 10401 images belonging to 2 classes.
Epoch 1/80
910/910 [==============================] - 2734s 3s/step - loss: 0.7040 - acc: 0.5013 - val_loss: 0.6932 - val_acc: 0.4954
Epoch 2/80
910/910 [==============================] - 2695s 3s/step - loss: 0.6828 - acc: 0.5328 - val_loss: 0.6468 - val_acc: 0.7468
Epoch 3/80
910/910 [==============================] - 2679s 3s/step - loss: 0.4579 - acc: 0.7945 - val_loss: 0.4675 - val_acc: 0.8666
Epoch 4/80
910/910 [==============================] - 2667s 3s/step - loss: 0.3446 - acc: 0.8569 - val_loss: 0.3827 - val_acc: 0.8927
Epoch 5/80
910/910 [==============================] - 2664s 3s/step - loss: 0.2788 - acc: 0.8879 - val_loss: 0.3008 - val_acc: 0.8986
Epoch 6/80
910/910 [==============================] - 2656s 3s/step - loss: 0.2364 - acc: 0.9089 - val_loss: 0.2759 - val_acc: 0.9199
Epoch 7/80
910/910 [==============================] - 2645s 3s/step - loss: 0.2071 - acc: 0.9195 - val_loss: 0.3080 - val_acc: 0.8625
Epoch 8/80
910/910 [==============================] - 2643s 3s/step - loss: 0.1901 - acc: 0.9261 - val_loss: 0.2992 - val_acc: 0.8557
Epoch 9/80
910/910 [==============================] - 2638s 3s/step - loss: 0.1764 - acc: 0.9325 - val_loss: 0.1919 - val_acc: 0.9312
Epoch 10/80
910/910 [==============================] - 2635s 3s/step - loss: 0.1677 - acc: 0.9364 - val_loss: 0.1718 - val_acc: 0.9365
Epoch 11/80
910/910 [==============================] - 2638s 3s/step - loss: 0.1595 - acc: 0.9397 - val_loss: 0.2178 - val_acc: 0.9054
Epoch 12/80
910/910 [==============================] - 2635s 3s/step - loss: 0.1494 - acc: 0.9425 - val_loss: 0.1538 - val_acc: 0.9450
Epoch 13/80
910/910 [==============================] - 2629s 3s/step - loss: 0.1462 - acc: 0.9447 - val_loss: 0.1488 - val_acc: 0.9519
Epoch 14/80
910/910 [==============================] - 2627s 3s/step - loss: 0.1382 - acc: 0.9470 - val_loss: 0.1574 - val_acc: 0.9391
Epoch 15/80
910/910 [==============================] - 2627s 3s/step - loss: 0.1358 - acc: 0.9494 - val_loss: 0.1436 - val_acc: 0.9477
Epoch 16/80
910/910 [==============================] - 2626s 3s/step - loss: 0.1319 - acc: 0.9499 - val_loss: 0.1417 - val_acc: 0.9479
Epoch 17/80