hzfan commented on a change in pull request #8622:
URL: https://github.com/apache/tvm/pull/8622#discussion_r681319482
##########
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:
@masahi My concern is that `linear` is supposed to support inputs with
arbitrary ranks like 1d, 2d, 3d, 4d.... The different input dimensions are
normalized in `self.matmul`. If `_op.nn.dense` is directly used, the usability
of `linear` would be limited to inputs whose ranks are 2.
--
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]
