def test_route_layer(): np.random.seed(123) batch, w, h, c = (1, 5, 5, 3) input = np.random.uniform(low=-10, high=10. ,size=(batch, w, h, c)) # from -10 to 10 to see both the effect of Relu and TanH activation # init keras model inp = Input(shape=(w, h, c), batch_shape=(batch, w, h, c)) x = Activation(activation='relu')(inp) y = Activation(activation='tanh')(x) Concat = Concatenate( axis=-1)([x, y]) # concatenate of x and y model = Model(inputs=[inp], outputs=Concat) # init NumPyNet model net = Network(batch=batch, input_shape=(w, h, c)) net.add(Activation_layer(activation='relu')) # layer 1 net.add(Activation_layer(activation='tanh')) # layer 2 net.add(Route_layer(input_layers=(1,2), by_channels=True)) net._fitted = True # False control # FORWARDS fwd_out_numpynet = net.predict(X=input) fwd_out_keras = model.predict(x=input, batch_size=batch) assert np.allclose(fwd_out_keras, fwd_out_numpynet) # ok net.fitted = False # the correct state of the network # BACKWARD # try some derivatives gradient = K.gradients(model.output, model.inputs) func = K.function(model.inputs + model.outputs ,gradient) delta_keras = func([input])[0] net._net[3].delta = np.ones(shape=fwd_out_numpynet.shape) net._backward(X=input) delta_numpynet = net._net[0].delta
def test_backward(self, b, w, h, c):
# TODO: test backward correctly
input = np.random.uniform(low=-10, high=10., size=(b, w, h, c))
tf_input = tf.Variable(input)
# init keras model
inp = Input(batch_shape=(b, w, h, c))
x = Activation(activation='relu')(inp)
y = Activation(activation='tanh')(x)
Concat = Concatenate(axis=-1)([x, y]) # concatenate of x and y
model = Model(inputs=[inp], outputs=Concat)
model.compile(optimizer='sgd', loss='mse')
# init NumPyNet model
net = Network(batch=b, input_shape=(w, h, c))
net.add(Activation_layer(activation='relu')) # layer 1
net.add(Activation_layer(activation='tanh')) # layer 2
net.add(Route_layer(input_layers=(1, 2), by_channels=True))
net.add(
Cost_layer(cost_type='mse',
scale=1.,
ratio=0.,
noobject_scale=1.,
threshold=0.,
smoothing=0.))
net.compile(optimizer=SGD())
net._fitted = True
# FORWARDS
fwd_out_numpynet = net.predict(X=input)
with tf.GradientTape() as tape:
preds = model(tf_input)
grads = tape.gradient(preds, tf_input)
fwd_out_keras = preds.numpy()
delta_keras = grads.numpy()
np.testing.assert_allclose(fwd_out_keras,
fwd_out_numpynet,
rtol=1e-5,
atol=1e-8)
net._fitted = False
# BACKWARD
net._net[3].delta = np.ones(shape=fwd_out_numpynet.shape, dtype=float)
net._backward(X=input)
delta_numpynet = net._net[0].delta
assert delta_numpynet.shape == delta_keras.shape
def test_printer(self, b, w, h, c):
net = Network(batch=b, input_shape=(w, h, c))
net.add(Activation_layer(activation='relu')) # layer 1
net.add(Activation_layer(activation='tanh')) # layer 2
net.add(Route_layer(input_layers=(1, 2), by_channels=True))
net.add(
Cost_layer(cost_type='mse',
scale=1.,
ratio=0.,
noobject_scale=1.,
threshold=0.,
smoothing=0.))
net.compile(optimizer=SGD())
net.summary()
def test_forward(self, b, w, h, c):
input = np.random.uniform(low=-10, high=10.,
size=(b, w, h, c)).astype(float)
# init keras model
inp = Input(batch_shape=(b, w, h, c))
x = Activation(activation='relu')(inp)
y = Activation(activation='tanh')(x)
Concat = Concatenate(axis=-1)([x, y]) # concatenate of x and y
model = Model(inputs=[inp], outputs=Concat)
model.compile(optimizer='sgd', loss='mse')
# init NumPyNet model
net = Network(batch=b, input_shape=(w, h, c))
net.add(Activation_layer(activation='relu')) # layer 1
net.add(Activation_layer(activation='tanh')) # layer 2
net.add(Route_layer(input_layers=(1, 2), by_channels=True))
net.add(
Cost_layer(cost_type='mse',
scale=1.,
ratio=0.,
noobject_scale=1.,
threshold=0.,
smoothing=0.))
net.compile(optimizer=SGD())
net.summary()
assert net._fitted == False
net._fitted = True # False control
# FORWARDS
fwd_out_numpynet = net.predict(X=input)
fwd_out_keras = model.predict(x=input, batch_size=b)
np.testing.assert_allclose(fwd_out_keras,
fwd_out_numpynet,
rtol=1e-5,
atol=1e-8)
############################################
n_train = X_train.shape[0]
n_test = X_test.shape[0]
# transform y to array of dimension 10 and in 4 dimension
y_train = to_categorical(y_train).reshape(n_train, 1, 1, -1)
y_test = to_categorical(y_test).reshape(n_test, 1, 1, -1)
# Create the model and training
model = Network(batch=batch, input_shape=X_train.shape[1:])
model.add(
Convolutional_layer(size=3,
filters=32,
stride=1,
pad=True,
activation='Relu'))
model.add(BatchNorm_layer())
model.add(Maxpool_layer(size=2, stride=1, padding=True))
model.add(Connected_layer(outputs=100, activation='Relu'))
model.add(BatchNorm_layer())
model.add(Connected_layer(outputs=num_classes, activation='Linear'))
model.add(Softmax_layer(spatial=True, groups=1, temperature=1.))
# model.add(Cost_layer(cost_type=cost_type.mse))
X = X.reshape(num_samples, 1, 1, size)
X_train, X_test = X[:train_size, ...], X[train_size:train_size+180, ...]
y_train, y_test = y[:train_size, ...], y[train_size:train_size+180, ...]
batch = 20
step = batch
y_train = y_train.reshape(-1, 1, 1, 1)
y_test = y_test.reshape(-1, 1, 1, 1)
# Create the model and training
model = Network(batch=batch, input_shape=X_train.shape[1:])
model.add(RNN_layer(outputs=32, steps=step, activation='linear'))
model.add(Connected_layer(outputs=8, activation='relu'))
model.add(Connected_layer(outputs=1, activation='linear'))
model.add(Cost_layer(cost_type='mse'))
# keras standard arguments
model.compile(optimizer=RMSprop(lr=0.001, epsilon=1e-7))#, metrics=[mean_absolute_error])
print('*************************************')
print('\n Total input dimension: {}'.format(X_train.shape), '\n')
print('**************MODEL SUMMARY***********')
model.summary()
print('\n***********START TRAINING***********\n')
# Fit the model on the training set
n_train = X_train.shape[0]
n_test = X_test.shape[0]
# transform y to array of dimension 10 and in 4 dimension
y_train = to_categorical(y_train).reshape(n_train, 1, 1, -1)
y_test = to_categorical(y_test).reshape(n_test, 1, 1, -1)
# Create the modeland training
model = Network(batch=batch, input_shape=X_train.shape[1:])
# model.add(Input_layer(input_shape=(batch, 32, 32, 3))) # not necessary if input_shape is given to Network
model.add(
Convolutional_layer(input_shape=(batch, 8, 8, 3),
size=3,
filters=32,
stride=1,
pad=True,
activation='Relu'))
model.add(
Convolutional_layer(input_shape=(batch, 8, 8, 32),
size=3,
filters=64,
stride=1,
pad=True,
activation='Relu'))
model.add(Maxpool_layer(size=2, stride=1, padding=True))
model.add(Dropout_layer(prob=0.25))
model.add(
Connected_layer(input_shape=(batch, 8, 8, 64),
outputs=128,