def layer_test(layer_cls,
kwargs={},
input_shape=None,
input_dtype=None,
input_data=None,
expected_output=None,
expected_output_dtype=None,
fixed_batch_size=False,
tolerance=1e-3):
"""Test routine for a layer with a single input tensor
and single output tensor.
"""
# generate input data
if input_data is None:
assert input_shape
if not input_dtype:
input_dtype = K.floatx()
input_data_shape = list(input_shape)
for i, e in enumerate(input_data_shape):
if e is None:
input_data_shape[i] = np.random.randint(1, 4)
input_data = (10 * np.random.random(input_data_shape))
input_data = input_data.astype(input_dtype)
else:
if input_shape is None:
input_shape = input_data.shape
if input_dtype is None:
input_dtype = input_data.dtype
if expected_output_dtype is None:
expected_output_dtype = input_dtype
# instantiation
layer = layer_cls(**kwargs)
# test get_weights , set_weights at layer level
weights = layer.get_weights()
layer.set_weights(weights)
# test and instantiation from weights
if 'weights' in inspect.getargspec(layer_cls.__init__):
kwargs['weights'] = weights
layer = layer_cls(**kwargs)
# test in functional API
if fixed_batch_size:
x = Input(batch_shape=input_shape, dtype=input_dtype)
else:
x = Input(shape=input_shape[1:], dtype=input_dtype)
y = layer(x)
assert K.dtype(y) == expected_output_dtype
# check shape inference
model = Model(x, y)
expected_output_shape = layer.compute_output_shape(input_shape)
actual_output = model.predict(input_data)
actual_output_shape = actual_output.shape
for expected_dim, actual_dim in zip(expected_output_shape,
actual_output_shape):
if expected_dim is not None:
assert expected_dim == actual_dim
if expected_output is not None:
if tolerance is not None:
assert_allclose(actual_output, expected_output, rtol=tolerance)
# test serialization, weight setting at model level
model_config = model.get_config()
recovered_model = Model.from_config(model_config)
if model.weights:
weights = model.get_weights()
recovered_model.set_weights(weights)
_output = recovered_model.predict(input_data)
if tolerance is not None:
assert_allclose(_output, actual_output, rtol=tolerance)
# test training mode (e.g. useful for dropout tests)
model.compile('rmsprop', 'mse')
model.train_on_batch(input_data, actual_output)
# test as first layer in Sequential API
layer_config = layer.get_config()
layer_config['batch_input_shape'] = input_shape
layer = layer.__class__.from_config(layer_config)
model = Sequential()
model.add(layer)
actual_output = model.predict(input_data)
actual_output_shape = actual_output.shape
for expected_dim, actual_dim in zip(expected_output_shape,
actual_output_shape):
if expected_dim is not None:
assert expected_dim == actual_dim
if expected_output is not None:
if tolerance is not None:
assert_allclose(actual_output, expected_output, rtol=1e-3)
# test serialization, weight setting at model level
model_config = model.get_config()
recovered_model = Sequential.from_config(model_config)
if model.weights:
weights = model.get_weights()
recovered_model.set_weights(weights)
_output = recovered_model.predict(input_data)
if tolerance is not None:
assert_allclose(_output, actual_output, rtol=1e-3)
# test training mode (e.g. useful for dropout tests)
model.compile('rmsprop', 'mse')
model.train_on_batch(input_data, actual_output)
# for further checks in the caller function
return actual_output
##### validation_split (in ImageDataGenerator) = 0.15
start_f = 15
depth = 5
model = tf.keras.Sequential()
for i in range(depth): #repete the block for depth times
if i == 0:
input_shape = [img_h, img_w, 3]
else:
input_shape=[None]
model.add(tf.keras.layers.Conv2D(filters=start_f,
kernel_size=(3,3),
strides=(1,1),
padding='same',
input_shape=input_shape))
model.add(tf.keras.layers.ReLU())
model.add(tf.keras.layers.MaxPool2D(pool_size=(2,2)))
start_f *=2
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(units=64, activation='relu'))
model.add(tf.keras.layers.Dense(units=num_classes, activation='softmax'))
# <<< WITHOUT TL
# In[ ]:
def layer_test(test_case, layer_cls, kwargs={}, input_shape=None, input_dtype=None,
input_data=None, expected_output=None,
expected_output_dtype=None, fixed_batch_size=False):
"""
Test routine for a layer with a single input tensor
and single output tensor.
"""
if input_data is None:
assert input_shape
if not input_dtype:
input_dtype = K.floatx()
input_data_shape = list(input_shape)
for i, e in enumerate(input_data_shape):
if e is None:
input_data_shape[i] = np.random.randint(1, 4)
input_data = (10 * np.random.random(input_data_shape))
input_data = input_data.astype(input_dtype)
elif input_shape is None:
input_shape = input_data.shape
if expected_output_dtype is None:
expected_output_dtype = input_dtype
# instantiation
layer = layer_cls(**kwargs)
# test get_weights , set_weights
weights = layer.get_weights()
layer.set_weights(weights)
# test and instantiation from weights
if 'weights' in inspect.getargspec(layer_cls.__init__):
kwargs['weights'] = weights
layer = layer_cls(**kwargs)
# test in functional API
if fixed_batch_size:
x = Input(batch_shape=input_shape, dtype=input_dtype)
else:
x = Input(shape=input_shape[1:], dtype=input_dtype)
y = layer(x)
test_case.assertEqual(K.dtype(y), expected_output_dtype)
model = Model(input=x, output=y)
model.compile('rmsprop', 'mse')
expected_output_shape = layer.get_output_shape_for(input_shape)
actual_output = model.predict(input_data)
actual_output_shape = actual_output.shape
for expected_dim, actual_dim in zip(expected_output_shape,
actual_output_shape):
if expected_dim is not None:
test_case.assertEqual(expected_dim, actual_dim)
if expected_output is not None:
assert_allclose(actual_output, expected_output, rtol=1e-3)
model = Sequential()
model.add(layer)
model.compile('rmsprop', 'mse')
actual_output = model.predict(input_data)
actual_output_shape = actual_output.shape
for expected_dim, actual_dim in zip(expected_output_shape,
actual_output_shape):
if expected_dim is not None:
test_case.assertEqual(expected_dim, actual_dim)
if expected_output is not None:
assert_allclose(actual_output, expected_output, rtol=1e-3)
# for further checks in the caller function
return actual_output
