def test_get_activation_map_shape_text(self):
activation_maps_shape = tuple(np.random.randint(low=1, high=10, size=3))
self.assertEqual(
masking._get_activation_map_shape(
activation_maps_shape, model_type='text_cnn'),
(activation_maps_shape[1], 1))
def test_get_activation_map_shape_image(self):
activation_maps_shape = tuple(np.random.randint(low=1, high=10, size=4))
self.assertEqual(
masking._get_activation_map_shape(
activation_maps_shape, model_type='cnn'),
(activation_maps_shape[1], activation_maps_shape[2]))
def test_formulate_smt_constraints_convolution_layer_text(self):
with self.test_session():
# Temporary graphs should be created inside a session. Notice multiple
# graphs are being created in this particular code. So, if each graph
# isn't created inside a separate session, the tensor names will have
# unwanted integer suffices, which then would cause problems while
# accessing tensors by name.
_create_temporary_tf_graph_text_cnn(self.test_model_path)
# The 1st convolution layer has 12 neurons.
image = np.ones(5)
tensor_names = {
'input': 'input_1:0',
'embedding': 'embedding/embedding_lookup/Identity_1:0',
'first_layer': 'conv1d/BiasAdd:0',
'first_layer_relu': 'conv1d/Relu:0',
'logits': 'dense/BiasAdd:0',
'softmax': 'dense/Sigmoid:0',
'weights_layer_1': 'conv1d/conv1d/ExpandDims_1:0',
'biases_layer_1': 'conv1d/BiasAdd/ReadVariableOp:0'
}
session = utils.restore_model(self.test_model_path)
cnn_predictions = session.run(
tensor_names,
feed_dict={tensor_names['input']: image.reshape(1, 5)})
text_embedding = masking._remove_batch_axis(
cnn_predictions['embedding'])
z3_mask = [
z3.Int('mask_%d' % i) for i in range(text_embedding.shape[0])
]
masked_input = []
for mask_bit, embedding_row in zip(z3_mask, text_embedding):
masked_input.append(
[z3.ToReal(mask_bit) * i for i in embedding_row])
first_layer_activations = masking._reorder(
masking._remove_batch_axis(
cnn_predictions['first_layer'])).reshape(-1)
z3_optimizer = masking._formulate_smt_constraints_convolution_layer(
z3_optimizer=utils.TextOptimizer(z3_mask=z3_mask),
kernels=masking._reshape_kernels(
kernels=cnn_predictions['weights_layer_1'],
model_type='text_cnn'),
biases=cnn_predictions['biases_layer_1'],
chosen_indices=first_layer_activations.argsort()[-5:],
conv_activations=first_layer_activations,
input_activation_maps=[masked_input],
output_activation_map_shape=masking._get_activation_map_shape(
activation_maps_shape=cnn_predictions['first_layer'].shape,
model_type='text_cnn'),
strides=1,
padding=(0, 0),
gamma=0.5)
mask, result = z3_optimizer.generate_mask()
self.assertEqual(result, 'sat')
self.assertEqual(mask.shape, (5, ))
session.close()
