onnx-simplifier
nn
Our great sponsors
onnx-simplifier | nn | |
---|---|---|
3 | 26 | |
3,483 | 46,249 | |
- | 7.2% | |
7.1 | 7.7 | |
25 days ago | 6 days ago | |
C++ | Jupyter Notebook | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
onnx-simplifier
-
Show: Cross-platform Image segmentation on video using eGUI, onnxruntime and ffmpeg
onnx-simplifier can shed some of incompatibilities in widespread use, but is itself bug ridden and lagging behind the standard. For any serious model, or when you don't get lucky simplifying the model upstream, you'd generally want good support of opset 11.
-
[Technical Article] OCR Upgrade
ONNX Simplifier:https://github.com/daquexian/onnx-simplifier
-
PyTorch 1.10
As far as I know, the ONNX format won't give you a performance boost on its own. However, there are ONNX optimizers for the ONNX runtime which will speed up your inference.
But if you are using Nvidia Hardware, then TensorRT should give you the best performance possible, especially if you change the precision level. Don't forget to simplify your ONNX model before you converting it to TensorRT though: https://github.com/daquexian/onnx-simplifier
nn
- [D] Looking for open source projects to contribute
-
PyTorch 1.10
We did a bunch of popular research paper implementations in PyTorch with notes (annotations); might be helpful.
-
[P] Annotated deep learning paper implementations
Website with side-by-side notes rendered: nn.labml.ai
You can create a pull request or start a discussion in GitHub issues. Even voting suggesting papers to implement and voting for them will be helpful. Here's a recent pull request for example
- PonderNet: Annotated PyTorch Implementation
-
Annotated PyTorch implementations of various deep learning normalization layers
Author here. From next month onwards we will pick papers to implement based on votes on Github issues https://github.com/lab-ml/nn/issues
Feel free to open an issue if there's a paper that you like implemented.
Git link: https://github.com/lab-ml/nn
I think this is awesome and personally cloned the repo so i can browse through the docs later without adding 'yet another tab' to my browser.
What are some alternatives?
GFPGAN-for-Video-SR - A colab notebook for video super resolution using GFPGAN
onnxruntime - ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
torch2trt - An easy to use PyTorch to TensorRT converter
PaddleOCR - Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
labml - 🔎 Monitor deep learning model training and hardware usage from your mobile phone 📱
functorch - functorch is JAX-like composable function transforms for PyTorch.
ZoeDepth - Metric depth estimation from a single image
TensorRT - PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
Basic-UI-for-GPT-J-6B-with-low-vram - A repository to run gpt-j-6b on low vram machines (4.2 gb minimum vram for 2000 token context, 3.5 gb for 1000 token context). Model loading takes 12gb free ram.
DFL-Colab - DeepFaceLab fork which provides IPython Notebook to use DFL with Google Colab
Behavior-Sequence-Transformer-Pytorch - This is a pytorch implementation for the BST model from Alibaba https://arxiv.org/pdf/1905.06874.pdf