cnn from scratch with keras - code review

This post gives a working sample of training neutral net with cnn in keras.

CNN setup is based on Yan LeCun configuration.

model = Sequential()

model.add(Conv2D(32, (3, 3), input_shape=input_shape))

model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(32, (3, 3)))

model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, (3, 3)))

model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())

model.add(Dense(64))

model.add(Activation('relu'))

model.add(Dropout(0.5))

model.add(Dense(1))

model.add(Activation('sigmoid'))

model.compile(loss='binary_crossentropy',

optimizer='rmsprop',

metrics=['accuracy'])

validation_generator = test_datagen.flow_from_directory(

validation_data_dir,

target_size=(img_width, img_height),

batch_size=batch_size,

class_mode='binary')

test_datagen is of type ImageDataGenerator which helps with generating batches of tensor image. The function "flow_from_directory" - extracts sample test images from a directory.

Since this is a sample classifying cat and dog, we will use a binary classification / accuracy as shown in code above


To predict (check if our model works), we use the following code :-

img = load_img('dog.jpg',False,target_size=(img_width,img_height))

x = img_to_array(img)

x = np.expand_dims(x, axis=0)

preds = model.predict_classes(x)

probs = model.predict_proba(x)