Comments (2)
Hi @anirudth, if your model is using non-fused BatchNormalization ops, support for this was added earlier today. Can you please retry with the latest code and see if you still encounter this issue?
Please note that we also only support BatchNorm ops created using tf slim or tf Keras apis. Can you provide any additional details about the model you are using?
from aimet.
Thanks for the quick reply. It seems to work.
from aimet.
Related Issues (20)
- tf1.15 perchannel error HOT 2
- In QAT "is_symmetric"=True but "offset" is not 0 or -128 so that cannot snpe-onnx-to-dlc model HOT 3
- AimetTensorQuantizer error HOT 5
- The export model is quantified model ? HOT 2
- names_to_exclude = [] # You need to populate this
- Significant Precision Loss Occurs Through DepthWiseConv2D on DSP HOT 2
- aimet_torch 1.28 can not export my onnx model normally HOT 12
- [Question] Static and Dynamic Quantization using AIMET HOT 5
- AttributeError: 'GraphModule' object has no attribute '_current_fx_name' HOT 1
- Not loading encodings for quantizer: ****** as it is disabled in Tensorflow framework HOT 1
- unable to run in google colab HOT 4
- aimet(torch1.9.1+cu111) got cuda error RuntimeError: merge_sort: failed to synchronize: cudaErrorIllegalAddress: an illegal m HOT 6
- google colab development doc outdated HOT 3
- support for pytorch 2.x? HOT 3
- Accept a wider range of versions for dependencies HOT 2
- Minor code updates
- Keras Model Preparer failing on subclass models
- pip 23.2 complains about "non-standard version number": aimet onnx-cpu-1.28.0
- how to ignore gru layer for Adaround.apply_adaround? HOT 6
- the inference time is slower than fp32 after quantize HOT 2
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.