def build_encoder(self, optimizer, loss_function):
encoder = NeuralNetwork(optimizer=optimizer, loss=loss_function)
encoder.add(Dense(512, input_shape=(self.img_dim, ), first_layer=True))
encoder.add(Activation('leaky_relu'))
#encoder.add(BatchNormalization(momentum=0.8))
encoder.add(Dense(256))
encoder.add(Activation('leaky_relu'))
#encoder.add(BatchNormalization(momentum=0.8))
encoder.add(Dense(self.latent_dim, latent_layer=True))
return encoder
def main():
def loadMNIST(prefix, folder):
intType = np.dtype('int32').newbyteorder('>')
nMetaDataBytes = 4 * intType.itemsize
data = np.fromfile(folder + "/" + prefix + '-images-idx3-ubyte', dtype='ubyte')
magicBytes, nImages, width, height = np.frombuffer(data[:nMetaDataBytes].tobytes(), intType)
data = data[nMetaDataBytes:].astype(dtype='float32').reshape([nImages, width, height])
labels = np.fromfile(folder + "/" + prefix + '-labels-idx1-ubyte',
dtype='ubyte')[2 * intType.itemsize:]
return data, labels
train, train_labels = loadMNIST("train", "./mnist/")
test, test_labels = loadMNIST("t10k", "./mnist/")
train = train.reshape((len(train), 784)) / 255.
test = test.reshape((len(test), 784)) / 255.
# print(train[0])
neural_net = NeuralNetwork()
neural_net.add(InputLayer(784))
neural_net.add(DenseLayer(30, activation="relu"))
neural_net.add(DenseLayer(10, activation="softmax"))
neural_net.initialize_weights(initializer="He")
# print(neural_net.weights[-1][:, 0])
neural_net.train(train, labels=train_labels.astype(int), loss="cross_entropy", learning_rate=0.1, epochs=10, mini_batch_size=8)
y = to_categorical(y.astype("int"))
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
# print(X_train.shape)
X_train = X_train[:256]
y_train = y_train[:256]
X_train = X_train.reshape((-1, 1, 8, 8))
X_test = X_test.reshape((-1, 1, 8, 8))
X_test = X_train[:256]
y_test = y_train[:256]
# Model
model = NeuralNetwork(SquareLoss(), (X_test, y_test))
model.add(
Conv2D(16,
filter_shape=(3, 3),
stride=1,
input_shape=(1, 8, 8),
padding='same'))
model.add(Activation('relu'))
model.add(Dropout(p=0.2))
model.add(Conv2D(n_filters=32, filter_shape=(3, 3), stride=1, padding='same'))
model.add(Activation('relu'))
model.add(Dropout(p=0.2))
model.add(Flatten())
model.add(Dense(256))
model.add(Activation('relu'))
model.add(Dropout(0.4))
model.add(Dense(10))
model.add(Activation('softmax'))
train_err = model.fit(X_train, y_train, n_epochs=5, batch_size=256)
def build_decoder(self, optimizer, loss_function):
decoder = NeuralNetwork(optimizer=optimizer, loss=loss_function)
decoder.add(Dense(256, input_shape=(self.latent_dim, )))
decoder.add(Activation('leaky_relu'))
decoder.add(BatchNormalization(momentum=0.8))
decoder.add(Dense(512))
decoder.add(Activation('leaky_relu'))
decoder.add(BatchNormalization(momentum=0.8))
decoder.add(Dense(self.img_dim))
decoder.add(Activation('tanh'))
return decoder
