Comments (2)
Hello @superpigforever, batchnorms are optimized out during conversion by folding the encoding values into the preceding conv2d (including depthwise and transpose variants) or fully connected layers. As such, the missing batchnorm operation is expected.
I would recommend a layer wise comparison between the fp32 model and the QNN quantized model. That could help narrow down the source of the regression.
from aimet.
Hi @superpigforever,
There are two points I would recommend checking:
1/ BN folding during QAT (using the method fold_all_batch_norms) => this is recommended to ensure consistency between QAT and hardware inference.
2/ Ensure that the encodings in the cpp file generated by qnn-onnx-converter contains the encodings coming from aimet QAT.
from aimet.
Related Issues (20)
- Modify quantizer type based on encoding provided when strict=False
- aimet common didn't release? HOT 5
- Missing save_as_external_data in OnnxSaver.save_initializer_restored_onnx_graph
- Torch batchnorm issue with Aimet 1.32.2
- AIMET 1.32 support for diffusers 1.28
- AIMET-TF-GPU Installation Issue
- CUDA ARCH 9.0 unsupported? HOT 7
- Memory Corruption Error: free(): invalid next size (fast) in bias_fold Method
- ImportError libpymo in AIMET 1.32 Pytorch 2.1.2+cu118 HOT 7
- CUDA ARCH 9.0 unsupported?
- RNN can not be quantized by aimet
- Fix device mismatch with blockwise api
- Added support for GridSample Op and made ScatterND op Jit tracable
- Unable to initialize class AimetTensorQuantizer: Cannot import AimetTensorQuantizer. Please build AimetTensorQuantizer and add artifact path to PYTHONPATH to resolve this issue HOT 2
- cache dataset is improperly built with inspect.param filed as defaults.
- Enable param renaming for export to onnx direct
- RmsNorm Op support
- I cannot install aimet-tf-cpu on ubuntu 20.04! HOT 2
- Register RmsNorm for quantization
- what's the quantization logic of LSTM
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from aimet.