def do_train():
dataset = np.ones(input_shape) # data to be fed as training
model = Sequential()
model.add(
Conv2D(
n_out,
(5, 5),
activation="relu",
input_shape=input_shape_conv,
use_bias=True,
weights=weights_bias,
name="conv",
))
model.add(Flatten()) # to handle Theano's categorical crossentropy
model.compile(optimizer="sgd", loss="categorical_crossentropy")
model.fit(
dataset,
np.ones(shape_out),
batch_size=1,
epochs=1,
callbacks=[
callbacks.DeadReluDetector(dataset, verbose=verbose)
],
verbose=False,
)
def test_DeadDeadReluDetector_activation():
"""
Tests that using "Activation" layer does not throw error
"""
input_data = Input(shape=(1, ))
output_data = Activation('relu')(input_data)
model = Model(input_data, output_data)
model.compile(optimizer='adadelta', loss='binary_crossentropy')
model.fit(np.array([[1]]),
np.array([[1]]),
epochs=1,
validation_data=(np.array([[1]]), np.array([[1]])),
callbacks=[callbacks.DeadReluDetector(np.array([[1]]))])
def do_train():
dataset = np.ones(input_shape) # data to be fed as training
model = Sequential()
model.add(
Dense(n_out,
activation='relu',
input_shape=input_shape_dense,
use_bias=False,
weights=[weights],
name='dense'))
model.compile(optimizer='sgd', loss='categorical_crossentropy')
model.fit(dataset,
np.ones(shape_out),
batch_size=1,
epochs=1,
callbacks=[
callbacks.DeadReluDetector(dataset, verbose=verbose)
],
verbose=False)
def do_test(weights, expected_warnings, verbose):
with warnings.catch_warnings(record=True) as w:
dataset = np.ones((1, 1, 1)) # data to be fed as training
model = Sequential()
model.add(
Dense(10,
activation='relu',
input_shape=(1, 1),
use_bias=False,
weights=[weights]))
model.compile(optimizer='sgd', loss='categorical_crossentropy')
model.fit(dataset,
np.ones((1, 1, 10)),
epochs=1,
callbacks=[
callbacks.DeadReluDetector(dataset, verbose=verbose)
],
verbose=False)
assert len(w) == expected_warnings
for warn_item in w:
assert issubclass(warn_item.category, RuntimeWarning)
assert "dead neurons" in str(warn_item.message)
