[Converter] Support GRU operator conversion with separated_rnn_gate_calc=False #323
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
|
Solved. |
|
Further optimization such as removing duplicate code & first time stamp Wh is on the way. |
Juelianqvq
changed the title
|
@peterjc123 cc |
peterjc123
reviewed
Jun 3, 2024
peterjc123
approved these changes
Jun 3, 2024
peterjc123
reviewed
Jun 3, 2024
| ops.append(tfl.FullyConnectedOperator([t, w_i, b_i], [input_mm])) | ||
| input_mm_list.append(input_mm) | ||
| ops.append(tfl.FullyConnectedOperator([h, w_h, b_h], [hidden_mm])) |
There was a problem hiding this comment.
This can be optimized if h is a constant. Let's do this in a follow-up PR.
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Outdated suggestions cannot be applied.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.
Some duplicate codes can be removed. But the most serious thing is to find out why all pytests failed with hints below:
AssertionError: The values for attribute 'shape' do not match: torch.Size([9, 1, 20]) != torch.Size([9, 0, 20]).i.e. You can run python converter_op_test.py -k test_gru_no_bias
Generated TFLite looks fine and Help wanted!