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)
def test_add_metrics(self):
check_function_equality = lambda f1, f2: f1.__code__.co_code == f2.__code__.co_code
custom_metrics_wrong = lambda y_true, y_pred, a: None
custom_metrics_default = lambda y_true, y_pred, a=3.14: None
model = Network(batch=42, input_shape=(1, 1, 1))
model.compile(optimizer=Adam(), metrics=[mean_accuracy_score])
assert model.metrics == [mean_accuracy_score]
assert all(
check_function_equality(x1, x2)
for x1, x2 in zip(model.metrics, [mean_accuracy_score]))
model.compile(optimizer=Adam(), metrics=[custom_metrics_default])
assert model.metrics == [custom_metrics_default]
assert all(
check_function_equality(x1, x2)
for x1, x2 in zip(model.metrics, [custom_metrics_default]))
with pytest.raises(MetricsError):
model.compile(optimizer=Adam(), metrics=[custom_metrics_wrong])
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))
# model.compile(optimizer=SGD(lr=0.01, decay=0., lr_min=0., lr_max=np.inf))
model.compile(optimizer=Adam(), metrics=[accuracy])
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
model.fit(X=X_train, y=y_train, max_iter=10, verbose=True)
print('\n***********START TESTING**************\n')
# Test the prediction with timing
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
model.fit(X=X_train, y=y_train.reshape(-1, 1, 1, 1), max_iter=10)
print('\n***********START TESTING**************\n')
# Test the prediction with timing
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))
# model.compile(optimizer=SGD(lr=0.01, decay=0., lr_min=0., lr_max=np.inf))
model.compile(optimizer=Adam(lr=1., decay=0.001), metrics=[accuracy])
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
model.fit(X=X_train, y=y_train, max_iter=10, verbose=True)
print('\n***********START TESTING**************\n')
# Test the prediction with timing
model.add(
Connected_layer(input_shape=(batch, 8, 8, 64),
outputs=128,
activation='Relu'))
model.add(Dropout_layer(prob=0.5))
model.add(
Connected_layer(input_shape=(batch, 1, 1, 128),
outputs=num_classes,
activation='Linear'))
model.add(Softmax_layer(spatial=True))
print('*************************************')
print('\n Total input dimension: {}'.format(X_train.shape), '\n')
print('*************************************')
model.compile(optimizer=Adam)
model.summary()
print('\n***********START TRAINING***********\n')
# Fit the model on the training set
model.fit(X=X_train, y=y_train, max_iter=5)
print('\n***********END TRAINING**************\n')
# Test the prediction
out = model.predict(X=X_test)
truth = y_test.argmax(axis=3).ravel()