comaniac commented on a change in pull request #8622:
URL: https://github.com/apache/tvm/pull/8622#discussion_r681252999
##########
File path: python/tvm/relay/frontend/pytorch.py
##########
@@ -1445,7 +1445,7 @@ def linear(self, inputs, input_types):
# 0 - input
# 1 - weight
bias = inputs[2]
- mm_out = self.matmul(inputs[:2], input_types[:2])
+ mm_out = self.matmul([inputs[0], _op.transpose(inputs[1], axes=(1,
0))], input_types[:2])
Review comment:
Maybe I missed something, does that mean the current linear layers
converted from PyTorch are wrong?
--
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]
