onnxruntime
onnxruntime copied to clipboard
microsoft
QDQ debugger - activations compare
Description: Debugger for QDQ loss part 1
Motivation and Context This is the first part of the QDQ debugger tool: activation comparison. The idea is that during quantization, we have an original float model and a qdq model. The debugger can run the two models side by side using the same input data. By comparing intermediate activations, we can help the model author figure out where the values differ, and take steps to reduce precision loss.
This pull request fixes 1 alert when merging f7619d57641694626338773b8888c54ce4020e6e into b2382dc43a92910c0e57fd4bfc31ed8649cd8521 - view on LGTM.com
fixed alerts:
- 1 for Unused import
![lgtm-com[bot] avatar](https://avatars.githubusercontent.com/in/17324?v=4 "Published by a pub.dev verified publisher"){kind=small}
This pull request fixes 1 alert when merging b74f20c7a6b011344ff5130eb473542d953912a1 into 24eab921bee4dbf9002942fbc514b2b2d9ee3a64 - view on LGTM.com
fixed alerts:
- 1 for Unused import
This pull request fixes 1 alert when merging d5a4b54d718d2224eac4064b7c325ac76dc50d86 into 24eab921bee4dbf9002942fbc514b2b2d9ee3a64 - view on LGTM.com
fixed alerts:
- 1 for Unused import
This pull request fixes 1 alert when merging a9de23bb557a74a6973d4c032009862c9049db11 into 24eab921bee4dbf9002942fbc514b2b2d9ee3a64 - view on LGTM.com
fixed alerts:
- 1 for Unused import
LGTM. Please fix the Lint/Python format issue. Just FYI. It can usually pass the check after running black and isort: https://github.com/microsoft/onnxruntime/blob/0c6037b5abe571fc43a55ef7a9d2f846820fbe5d/docs/Coding_Conventions_and_Standards.md#python-code-style
LGTM. Please fix the Lint/Python format issue. Just FYI. It can usually pass the check after running black and isort: https://github.com/microsoft/onnxruntime/blob/0c6037b5abe571fc43a55ef7a9d2f846820fbe5d/docs/Coding_Conventions_and_Standards.md#python-code-style
I did run black and isort before each commit. still got those errors. I might have some configuration issues that I don't know about.
Many false positive in our pipeline linter though, it can't recognize onnx module, so any onnx reference would result in error.
This pull request fixes 1 alert when merging e517fc2549946be095781d34e95de1aca6fd9a60 into 24eab921bee4dbf9002942fbc514b2b2d9ee3a64 - view on LGTM.com
fixed alerts:
- 1 for Unused import
This pull request fixes 1 alert when merging 65dcdba9b00aef3167923d75cd69ae7c8a56e1db into 580f2294bc50556a8e70cbaa02d39c595442efed - view on LGTM.com
fixed alerts:
- 1 for Unused import
This pull request fixes 1 alert when merging 47f203d8d9ab6369fa7754994ff37ee3d5d24327 into 73da3f3705003bf4e4d872047a4fabb8c1856243 - view on LGTM.com
fixed alerts:
- 1 for Unused import