Open cheyennee opened 6 months ago
In following code, pooling_window_shape is a tuple with 0, C.pooling crash.
pooling_window_shape
C.pooling
repo code:
img = np.reshape(np.arange(16, dtype=np.float32), [1, 4, 4]) x = C.input_variable(img.shape) layer = C.pooling(operand=x, pooling_type=C.MAX_POOLING, pooling_window_shape=(2,0), strides=(1), ceil_out_dim=True, include_pad=True, auto_padding=[True]).eval({x : [img]}) print(layer)
Same problem can be found in C.AVG_POOLING
C.AVG_POOLING
In following code,
pooling_window_shape
is a tuple with 0,C.pooling
crash.repo code: