[TFLite] add support for float16 #7093
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
|
It would be nice to supply testing. |
|
I've added a test. |
giuseros
reviewed
Dec 14, 2020
|
Is there something else I should fix or change? |
giuseros
requested changes
Dec 18, 2020
giuseros
approved these changes
Dec 18, 2020
There was a problem hiding this comment.
Thanks @euntaik ! This LGTM now. @FrozenGene , please feel free to merge if it's ok for you as well
FrozenGene
approved these changes
Dec 18, 2020
|
Thanks @euntaik @giuseros @FrozenGene ! |
masahi
pushed a commit
to masahi/tvm
that referenced
this pull request
Dec 24, 2020
* [TFLite] add support for float16 * add testi case * add test case * add comments
TusharKanekiDey
pushed a commit
to TusharKanekiDey/tvm
that referenced
this pull request
Jan 20, 2021
* [TFLite] add support for float16 * add testi case * add test case * add comments
trevor-m
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Jan 21, 2021
* [TFLite] add support for float16 * add testi case * add test case * add comments
electriclilies
pushed a commit
to electriclilies/tvm
that referenced
this pull request
Feb 18, 2021
* [TFLite] add support for float16 * add testi case * add test case * add comments
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Outdated suggestions cannot be applied.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.
Add support for float16
TFLite converts float32 models to float16 models by introducing a Dequantize op in every op that contains a float32 values (weights, biases, and constants etc. ).
So conv2d op should account for the weights and bias as an input tensor instead of a weight value attached to itself.