Fix ComputePropagateScalesMkldnnPass of MKLDNN #47574
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
|
你的PR提交成功，感谢你对开源项目的贡献! |
wozna
approved these changes
Nov 2, 2022
| auto new_pair = std::make_pair(pair.first, tmp_tensor); | ||
| var_quant_scales->insert(std::make_pair(input_name, new_pair)); | ||
| const auto scale = PADDLE_GET_CONST(float, op_node->Op()->GetAttr("scale")); | ||
| if (std::abs(scale) < 1e-6 && out_iter != var_quant_scales->end()) { |
There was a problem hiding this comment.
Did you find any example where the scale was so small?
There was a problem hiding this comment.
I didn't find so many cases, but when out_iter != var_quant_scales->end(), we need to divide, so add this judgment to avoid crashes
| @@ -336,27 +336,46 @@ void ComputePropagateScalesMkldnnPass::ComputeWeightScales( | |||
| ComputeLstmWeightScales(graph, scope, "WeightX", "WeightH", var_quant_scales); | |||
| } | |||
|
|
|||
| void ComputePropagateScalesMkldnnPass::UpdateScaleOpInScale( | |||
| void ComputePropagateScalesMkldnnPass::UpdateScaleOpInOutScales( | |||
There was a problem hiding this comment.
I think that for a new quantization method where there is linear_quantize before and and linear_dequantize after each operator this UpdateScaleOp it is no longer needed so much.
jiangjiajun
approved these changes
Nov 3, 2022
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Outdated suggestions cannot be applied.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.
PR types
Bug fixes
PR changes
Others
Describe
Fix ComputePropagateScalesMkldnnPass of MKLDNN