Comments (4)
An onnx model supported by TensorRT should looks like
But in your case, extra Identitiy are added to Q/DQ
We found that this would happened if Pytorch version == 1.12 . So if you are using the newest pytorch, you can try Pytorch 1.9, 1.10 or 1.11 to see if it could solve your problem.
from sparsebit.
Thanks, my question is sloved!
from sparsebit.
Can you upload your onnx in google drive or baidu?
from sparsebit.
QDQonnx. i upload qresnet20 from example ptq, qresnet18 , qmobilenetv2 from homework.
The docker I have tried are nvcr.io/nvidia/tensorrt:22.07-py3(8.4), nvcr.io/nvidia/tensorrt:22.05-py(8.2) and nvcr.io/nvidia/tensorrt:21:09-py(8.0)
from sparsebit.
Related Issues (20)
- torchvision densenet121 无法转成 sparsebit QuantModel HOT 4
- implementation for FQ-ViT HOT 3
- torchvision mobilenet_v2 导出 4w4f onnx 报错
- swin transformer HOT 1
- RuntimeError: Ninja is required to load C++ extensions
- KeyError: 'onnx::QuantizeLinear_711'
- Error in QAT train with DDP mode. HOT 2
- error when running generate.py under alpaca-lama HOT 1
- 我对你们的2080ti pipeline很感兴趣 HOT 2
- I wonder if the qlora do not support quantized models with groupsize!=-1 HOT 2
- errors using qViT.onnx to do inference HOT 1
- ImportError HOT 1
- An error about "x_dq = self._forward(x, scale, zero_point) " HOT 1
- A bug may have been resolved. HOT 3
- Should we install a full-version cuda instead of an anaconda-version cuda-toolkit? HOT 1
- How to deal with layers constructed by bool operations? HOT 1
- encounter keyerror when inputing module HOT 5
- How could I reproduce the results of QAT_DeiT on ImageNet? HOT 2
- QAT cifar10 example 报错 HOT 1
- QAT cifar10 example with QADD Quant enable 报错 HOT 1
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 sparsebit.