Fix PyTorch matmul conversion when given (2-dim, N-dim) input pair #7845
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Update repo
jcf94
requested changes
Apr 14, 2021
comaniac
reviewed
Apr 14, 2021
comaniac
approved these changes
Apr 14, 2021
jcf94
approved these changes
Apr 14, 2021
| @@ -162,7 +162,7 @@ def measure_latency(model, input_shapes, output_shapes, thresh, dryruns=40): | |||
| return est | |||
|
|
|||
|
|
|||
| def verify_model(model_name, input_data=[], custom_convert_map={}, rtol=1e-5, atol=1e-5): | |||
| def verify_model(model_name, input_data=[], custom_convert_map={}, rtol=1e-5, atol=1e-5, expected_ops=[]): | |||
wweic
approved these changes
Apr 14, 2021
|
@wweic it seems no conflict to the main branch? Please feel free to merge it. |
masahi
approved these changes
Apr 15, 2021
mehrdadh
pushed a commit
to mehrdadh/tvm
that referenced
this pull request
Apr 22, 2021
…pache#7845) * [AutoScheduler] Fix incorrectly array context device and hide info at the beginning * Lint fix * Lint fix * update repo * Fix Pytorch matmul conversion when given (2-dim, N-dim) input pair * update measure.py * Lint fix * fix bug && add ut for pytorch matmul * update ut * Lint fix * update commit * Lint fix
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
May 6, 2021
…pache#7845) * [AutoScheduler] Fix incorrectly array context device and hide info at the beginning * Lint fix * Lint fix * update repo * Fix Pytorch matmul conversion when given (2-dim, N-dim) input pair * update measure.py * Lint fix * fix bug && add ut for pytorch matmul * update ut * Lint fix * update commit * Lint fix
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
May 6, 2021
…pache#7845) * [AutoScheduler] Fix incorrectly array context device and hide info at the beginning * Lint fix * Lint fix * update repo * Fix Pytorch matmul conversion when given (2-dim, N-dim) input pair * update measure.py * Lint fix * fix bug && add ut for pytorch matmul * update ut * Lint fix * update commit * Lint fix
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
May 6, 2021
…pache#7845) * [AutoScheduler] Fix incorrectly array context device and hide info at the beginning * Lint fix * Lint fix * update repo * Fix Pytorch matmul conversion when given (2-dim, N-dim) input pair * update measure.py * Lint fix * fix bug && add ut for pytorch matmul * update ut * Lint fix * update commit * Lint fix
trevor-m
pushed a commit
to neo-ai/tvm
that referenced
this pull request
May 11, 2021
…pache#7845) * [AutoScheduler] Fix incorrectly array context device and hide info at the beginning * Lint fix * Lint fix * update repo * Fix Pytorch matmul conversion when given (2-dim, N-dim) input pair * update measure.py * Lint fix * fix bug && add ut for pytorch matmul * update ut * Lint fix * update commit * Lint fix
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR change the matmul conversion in PyTorch when given (2-dim, N-dim) input pair (N>2).
Original implement conversion [2 dim matrix * 3 dim tensor] into [batch matmul], however it can be implemented by a simple [matmul] with [2 dim matrix * 2 dim matrix (reshape 3 dim tensor into 2 dim matrix)].
cc @jcf94