[QNN] Align output_scale/zero_point of sigmoid to Torch #12624
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
|
Interesting, this might explain the large accuracy difference I saw between TVM and PT when running quantized mobilenet v3 model. |
masahi
reviewed
Aug 29, 2022
| output_scale = _expr.const(inputs[1]) | ||
| output_zero_point = _expr.const(inputs[2]) | ||
| input_scale = _expr.const(inputs[3]) | ||
| input_zero_point = _expr.const(inputs[4]) |
There was a problem hiding this comment.
Are you sure that output params occur before input? Your change seem to be calling _add_output_quant_params_to_sigmoid_op after we call _get_quant_param_for_input, which adds the input qparams first?.
There was a problem hiding this comment.
Yes. One example printing the inputs[1-4] is 0.00390625, 0, 0.09818686544895172, 96 , in which 0.00390625, 0 are the fixed output's scale/zp.
The index of output quantized params is set on Line 275: "aten::sigmoid": (1, 2),
masahi
approved these changes
Aug 29, 2022
xinetzone
pushed a commit
to daobook/tvm
that referenced
this pull request
Nov 25, 2022
* [QNN] Align output_scale/zero_point of sigmoid to Torch * [QNN] Align output_scale/zero_point of sigmoid to Torch
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Outdated suggestions cannot be applied.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.
Align output_scale/zero_point of sigmoid to Torch.
cc @masahi