Edge AI model training, quantization, compilation/benchmark & Model Zoo
- Git branch: r10.0
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.
Our documentation landing pages are the following:
- https://www.ti.com/edgeai : Technology page summarizing TI’s edge AI software/hardware products
- https://github.com/TexasInstruments/edgeai : Landing page for developers to understand overall software and tools offering. Read it before navigating into this repository.
- The subcomponents have detailed documentation. In the browser, navigate into the sub-folders to see detailed documentation. Here is a high level overview.
| Category | ToolLink | Purpose | IS NOT |
|---|---|---|---|
| Model Zoo / Models collection | edgeai-modelzoo | provides collection of pretrained models | |
| Model compilation & benchmarking | edgeai-benchmark | Wrapper on top of edgeai-tidl-tools for easy model compilation and speed/accuracy benchmarking - Bring your own model and compile, benchmark and generate artifacts for deployment on SDK with camera, inference and display (using edgeai-gst-apps) - Comprehends inference pipeline including dataset loading, pre-processing and post-processing - Benchmarking of accuracy and latency with large data sets - Post training quantization - Docker for easy development environment setup |
|
| Model training tools | edgeai-modeloptimization | Model optimization tools for improved model training, tools to train TIDL friendly models. - Model surgery: Modifies models with minimal loss in accuracy and makes it suitable for TI device (replaces unsupported operators) - QAT: Quantization Aware Training to improve accuracy with fixed point quantization - Model Pruning/sparsity: Induces sparsity during training – only applicable for specific devices - this is in development. |
- Does not support Tensorflow |
| Model training & code | edgeai-torchvision edgeai-mmdetection edgeai-mmdetection3d edgeai-hf-transformers edgeai-mmpose edgeai-yolox |
Training repositories for various tasks - 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 & Compilation | edgeai-modelmaker | Beginner friendly, command line, integrated environment for training & compilation - Bring your own data, select a model, perform training and generate artifacts for deployment on SDK - 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-modelmaker | edgeai-datasets | Example datasets |
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.