jiangjiajun commented on a change in pull request #9295:
URL: https://github.com/apache/tvm/pull/9295#discussion_r734444151
##########
File path: python/tvm/relay/frontend/paddlepaddle.py
##########
@@ -248,24 +287,13 @@ def convert_conv2d(g, op, block):
if padding_algorithm == "VALID":
paddings = [0, 0]
elif padding_algorithm == "SAME":
- if strides[0] == 1 and strides[1] == 1:
- pad_h = _get_pad_size(0, (k_h - 1) * dilations[0] + 1, strides[0])
- pad_w = _get_pad_size(0, (k_w - 1) * dilations[1] + 1, strides[1])
- else:
- input_shape = shape_of(input_x)
- h_w = _op.strided_slice(input_shape, [2], [4])
- try:
- in_h, in_w = infer_value(h_w, g.get_params()).numpy().tolist()
- except Exception as e:
- msg = "Dynamic shape is not supported in SAME padding
algorithm while stride!=1"
- raise tvm.error.OpAttributeInvalid(msg) from e
- pad_h = _get_pad_size(in_h, (k_h - 1) * dilations[0] + 1,
strides[0])
- pad_w = _get_pad_size(in_w, (k_w - 1) * dilations[1] + 1,
strides[1])
- paddings = [pad_h[0], pad_w[0], pad_h[1], pad_w[1]]
+ dilations = [1, 1]
Review comment:
This is a history issue for Paddle framework, while padding==`SAME`, it
will force dliations == 1
Here is the implementation code
https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/fluid/operators/conv_op.h#L113
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
