[Frontend][TFLite] Dynamically calculate input_stats of any fake_quant range #4789
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
* pass the input range to the convertor and caclulate (mean, scale) there * change the range of the second tensor in elemwise operations so that we test inputs with different quant params * change the possible output range for elemwise ops wrt the updated ranges * update the comments for (m, s) calculations * add input range dict to reduce_mean op
|
@kevinthesun @anijain2305 can you please take a look |
This was referenced Feb 3, 2020
anijain2305
reviewed
Feb 3, 2020
wyc-ruiker
suggested changes
Feb 4, 2020
anijain2305
approved these changes
Feb 4, 2020
There was a problem hiding this comment.
LGTM
@kevinthesun Can this be merged?
Edit - @inadob Seems like your newly added assertion is getting triggered. Can you please fix it?
* add exception handling for zero division in input_stats * fix range of the input tensor in elemwsie
|
Thanks @inadob @wyc-ruiker @anijain2305 |
alexwong
pushed a commit
to alexwong/tvm
that referenced
this pull request
Feb 26, 2020
…t range (apache#4789) * [TFLite] Dynamically calculate input_stats of any fake_quant range * pass the input range to the convertor and caclulate (mean, scale) there * change the range of the second tensor in elemwise operations so that we test inputs with different quant params * change the possible output range for elemwise ops wrt the updated ranges * update the comments for (m, s) calculations * add input range dict to reduce_mean op * Apply requested changes * add exception handling for zero division in input_stats * fix range of the input tensor in elemwsie
alexwong
pushed a commit
to alexwong/tvm
that referenced
this pull request
Feb 28, 2020
…t range (apache#4789) * [TFLite] Dynamically calculate input_stats of any fake_quant range * pass the input range to the convertor and caclulate (mean, scale) there * change the range of the second tensor in elemwise operations so that we test inputs with different quant params * change the possible output range for elemwise ops wrt the updated ranges * update the comments for (m, s) calculations * add input range dict to reduce_mean op * Apply requested changes * add exception handling for zero division in input_stats * fix range of the input tensor in elemwsie
zhiics
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Mar 2, 2020
…t range (apache#4789) * [TFLite] Dynamically calculate input_stats of any fake_quant range * pass the input range to the convertor and caclulate (mean, scale) there * change the range of the second tensor in elemwise operations so that we test inputs with different quant params * change the possible output range for elemwise ops wrt the updated ranges * update the comments for (m, s) calculations * add input range dict to reduce_mean op * Apply requested changes * add exception handling for zero division in input_stats * fix range of the input tensor in elemwsie
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.
so that we test inputs with different quant params