def test_cast(self):
"""Test that layers can automatically reshape inconsistent inputs."""
value1 = np.random.uniform(size=(2, 1)).astype(np.float32)
with self.session() as sess:
out_tensor = Cast(dtype=tf.int32)(tf.constant(value1))
result = out_tensor.eval()
assert result.dtype == np.int32
def test_cast(self):
"""Test that layers can automatically reshape inconsistent inputs."""
value1 = np.random.uniform(size=(2, 1)).astype(np.float32)
with self.session() as sess:
out_tensor = Cast(dtype=tf.int32)(tf.constant(value1))
result = out_tensor.eval()
assert result.dtype == np.int32
def test_Cast_pickle(): tg = TensorGraph() feature = Feature(shape=(tg.batch_size, 1)) layer = Cast(in_layers=feature, dtype=tf.int32) tg.add_output(layer) tg.set_loss(layer) tg.build() tg.save()
def create_loss(self, layer, label, weight):
task_label = Squeeze(squeeze_dims=1, in_layers=[label])
task_label = Cast(dtype=tf.int32, in_layers=[task_label])
task_weight = Squeeze(squeeze_dims=1, in_layers=[weight])
loss = SparseSoftMaxCrossEntropy(in_layers=[task_label, layer])
weighted_loss = WeightedError(in_layers=[loss, task_weight])
return weighted_loss