C = torch.cat((A,B),1)
张量的形状:
A is (1, 128, 128, 256)
B is (1, 1, 128, 256)
期望值C
为(1, 129, 128, 256)
此代码在 pytorch 上运行,但在转换为 core-ml 时,它给了我以下错误:
"Error while converting op of type: {}. Error message: {}\n".format(node.op_type, err_message, )
TypeError: Error while converting op of type: Concat. Error message: unable to translate constant array shape to CoreML shape"