n-nez opened a new pull request #5451: URL: https://github.com/apache/incubator-tvm/pull/5451
Symptoms ``` Traceback (most recent call last): File "test_forward.py", line 1646, in <module> test_forward_transpose() File "test_forward.py", line 755, in test_forward_transpose verify_model(Transpose3().float().eval(), input_data=input_data) File "test_forward.py", line 175, in verify_model custom_convert_map) File "/home/nnez/devel/public-tvm/python/tvm/relay/frontend/pytorch.py", line 2117, in from_pytorch outputs, ret_name, convert_map, prelude) File "/home/nnez/devel/public-tvm/python/tvm/relay/frontend/pytorch.py", line 2031, in convert_operators relay_out = relay_op(inputs, _get_input_types(op_node)) File "/home/nnez/devel/public-tvm/python/tvm/relay/frontend/pytorch.py", line 780, in _impl return _op.transform.transpose(data, axes) File "/home/nnez/devel/public-tvm/python/tvm/relay/op/transform.py", line 125, in transpose axes = list(axes) ``` This happens because of the current implementation of `prim::ListConstruct` translates a list of integer into `relay.Var` with the list encoded as the shape of it. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org