Fixes onnx Slice unintentional cast behavior #4319
Merged
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
|
This branch currently is behind tinygrad/master. The line count difference bot is disabled. |
geohotstan
changed the title
|
should not put fix in description as that would close the issue. i am surprise the test case does not cover this. are we disabling it? |
ah crap sorry, yeah the test suite does not test for different dtypes unless if the OP is dtype related. |
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Outdated suggestions cannot be applied.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.
fixes #4314
few notes:
This only addresses the reshape error
The reason of the error is that there is a previous
slice opthat uses a largeTensor(9223372036854775807, dtype=dtypes.long)as theendvalue, so theTensor.ceil()used sets it to 0After this is fixed, this model also requires
Exception: op_type ScatterND not supportedto run. I remember trying to write a ScatterND but being stuck at some cases.