You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2022/05/30 07:55:23 UTC
[GitHub] [tvm] hope51607 opened a new pull request, #11507: [Frontend][ONNX] Fix softmax converter when input shape is dynamic
hope51607 opened a new pull request, #11507:
URL: https://github.com/apache/tvm/pull/11507
When I run the onnx version mobilenet_v1 from [here](https://zenodo.org/record/3157894) without freeze_params, I meet an error:
```
tvm/python/tvm/relay/frontend/onnx.py:6006: in _convert_operator
sym = convert_map[op_name](inputs, attrs, self._params)
tvm/python/tvm/relay/frontend/onnx.py:2426: in _impl_v1
data_reshape = _op.reshape(inputs[0], newshape=reshape_shape)
...
if isinstance(newshape, (tuple, list)):
tempshape = []
print("newshape: ", newshape)
for shape in newshape:
if isinstance(shape, _expr.IntImm):
tempshape.append(shape.value)
else:
try:
print("shape: ", shape)
> tempshape.append(int(shape))
E TypeError: int() argument must be a string, a bytes-like object or a number, not 'Any'
tvm/python/tvm/relay/op/transform.py:311: TypeError
```
This is caused by Softmax encountering an input with a dynamic shape and using it to construct reshape.
I think simple solution is to directly create Softmax when axis==-1.
I also rewrite the Softmax test to cover dynamic case.
@blackkker @AndrewZhaoLuo @mbrookhart please give it a look.
Thanks for contributing to TVM! Please refer to guideline https://tvm.apache.org/docs/contribute/ for useful information and tips. After the pull request is submitted, please request code reviews from [Reviewers](https://github.com/apache/incubator-tvm/blob/master/CONTRIBUTORS.md#reviewers) by @ them in the pull request thread.
--
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: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] AndrewZhaoLuo merged pull request #11507: [Frontend][ONNX] Fix softmax converter when input shape is dynamic
Posted by GitBox <gi...@apache.org>.
AndrewZhaoLuo merged PR #11507:
URL: https://github.com/apache/tvm/pull/11507
--
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: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] hope51607 commented on pull request #11507: [Frontend][ONNX] Fix softmax converter when input shape is dynamic
Posted by GitBox <gi...@apache.org>.
hope51607 commented on PR #11507:
URL: https://github.com/apache/tvm/pull/11507#issuecomment-1143520351
Hi @AndrewZhaoLuo, thanks for your reply.
Consider the testing relay graph
```
def @main(%in: Tensor[(1, 10), float32], %shape: Tensor[(2), int64]) {
%0 = dyn.reshape(%in, %shape, newshape=[]);
nn.softmax(%0, axis=1)
}
```
I found that when the target is cuda, the TIR lowering from softmax contains
```
allocate(T_softmax_exp: Pointer(warp float32), float32, [any_dim_3]), storage_scope = warp;
```
which seems to allocate warp memory with any.
I am not sure why the reason behind the problem is that cuda's softmax does not support dynamic shapes? or is it a softmax schedule issue?
I think this issue seems to be out of scope of this PR.
Maybe I should mark skip in these softmax tests with dynamic shapes when target is cuda.
Can anyone give me some hints?
Thanks.
--
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: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] AndrewZhaoLuo commented on pull request #11507: [Frontend][ONNX] Fix softmax converter when input shape is dynamic
Posted by GitBox <gi...@apache.org>.
AndrewZhaoLuo commented on PR #11507:
URL: https://github.com/apache/tvm/pull/11507#issuecomment-1143880119
I'm not aware of dynamism support for softmax in CUDA but my guess is it's a schedule issue. I'm fine with you marking the dynamic tests as skip with cuda target. Just add a TODO please
--
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: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] hope51607 commented on pull request #11507: [Frontend][ONNX] Fix softmax converter when input shape is dynamic
Posted by GitBox <gi...@apache.org>.
hope51607 commented on PR #11507:
URL: https://github.com/apache/tvm/pull/11507#issuecomment-1144499906
@AndrewZhaoLuo got it. I've marked cuda as xfailed and added a TODO comment.
--
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: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org