Home

Awesome

edgeai-tensorlab

Edge AI model training, quantization, compilation/benchmark & Model Zoo

<hr>

Release 10.0 (10_00) Update 2

More details and information about previous releases are available in Release Notes

It is important to use the correct git branch (matching with the SDK version) if you are going to use the compiled models on a device/EVM.

<hr>

Notice

Our documentation landing pages are the following:

<hr> <hr>

Components

CategoryToolLinkPurposeIS NOT
Model Zoo / Models collectionedgeai-modelzooprovides collection of pretrained models
Model compilation & benchmarkingedgeai-benchmarkWrapper on top of edgeai-tidl-tools for easy model compilation and speed/accuracy benchmarking<br>- Bring your own model and compile, benchmark and generate artifacts for deployment on SDK with camera, inference and display (using edgeai-gst-apps)<br>- Comprehends inference pipeline including dataset loading, pre-processing and post-processing<br>- Benchmarking of accuracy and latency with large data sets<br>- Post training quantization<br>- Docker for easy development environment setup
Model training toolsedgeai-modeloptimizationModel optimization tools for improved model training, tools to train TIDL friendly models.<br>- Model surgery: Modifies models with minimal loss in accuracy and makes it suitable for TI device (replaces unsupported operators)<br>- QAT: Quantization Aware Training to improve accuracy with fixed point quantization<br>- Model Pruning/sparsity: Induces sparsity during training – only applicable for specific devices - this is in development.<br>- Does not support Tensorflow
Model training & codeedgeai-torchvision<br>edgeai-mmdetection<br>edgeai-mmdetection3d<br>edgeai-hf-transformers<br>edgeai-mmpose<br>edgeai-yoloxTraining repositories for various tasks<br>- Provides extensions of popular training repositories (like mmdetection, torchvision) with lite version of models- Does not support Tensorflow
End-to-end Model development - Datasets, Training & Compilationedgeai-modelmakerBeginner friendly, command line, integrated environment for training & compilation<br>- Bring your own data, select a model, perform training and generate artifacts for deployment on SDK<br>- Backend tool for model composer (early availability of features compared to Model Composer )- Does not support Bring Your Own Model workflow
Example datasets, used in edgeai-modelmakeredgeai-datasetsExample datasets
<hr> <hr>

Tech Reports

Technical documentation can be found in the documentation of each repository. Here we have a collection of technical reports & tutorials that give high level overview on various topics - see Edge AI Tech Reports.

<hr>