diff options
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 16 |
1 files changed, 9 insertions, 7 deletions
| @@ -15,14 +15,15 @@ Please see [LICENSE](./LICENSE) file. | |||
| 15 | 15 | ||
| 16 | ## Installation | 16 | ## Installation |
| 17 | 17 | ||
| 18 | This repository requires **mmdet** Python package from mmdetection to be installed. | 18 | This repository requires [**mmdetection**](https://github.com/open-mmlab/mmdetection) and [**mmcv**](https://github.com/open-mmlab/mmcv) to be installed. |
| 19 | 19 | ||
| 20 | Please refer to [installation instructions for mmdetection](https://github.com/open-mmlab/mmdetection/blob/master/docs/install.md) for installation instructions and also for dataset preparation. If you get any issues with the master branch of mmdetection, please try after checking out the latest release tag. | 20 | Please refer to [installation instructions for mmdetection](https://github.com/open-mmlab/mmdetection/blob/master/docs/install.md) for installation instructions. If you get any issues with the master branch of mmdetection, please try after checking out the latest release tag. After installation, a python package called "mmdet" will be listed if you do *pip list* |
| 21 | 21 | ||
| 22 | Note: mmdetection also requreis **mmcv** and several other dependencies to be installed as described in the above URL. | 22 | To install mmcv, browse to the github page of [mmcv](https://github.com/open-mmlab/mmcv), and see the section that says "**Install with pip**". Install the full version of mmcv using the instruction given there. Please check your CUDA version and PyTorch version and select the appropriate installation instructions. |
| 23 | 23 | ||
| 24 | After installing **mmdet**, please clone and install [**PyTorch-Jacinto-AI-DevKit**](https://git.ti.com/cgit/jacinto-ai/pytorch-jacinto-ai-devkit/about/) using the link given in [jacinto-ai-devkit](https://github.com/TexasInstruments/jacinto-ai-devkit) as this repository uses several components from there - especially to define low complexity models and to do Quantization Aware Training (QAT) or Calibration. | 24 | After installing **mmdetection** and **mmcv**, please clone and install [**PyTorch-Jacinto-AI-DevKit**](https://git.ti.com/cgit/jacinto-ai/pytorch-jacinto-ai-devkit/about/) using the link given in [jacinto-ai-devkit](https://github.com/TexasInstruments/jacinto-ai-devkit) as this repository uses several components from there - especially to define low complexity models and to do Quantization Aware Training (QAT) or Calibration. |
| 25 | 25 | ||
| 26 | Please see our minimal installation script [setup.sh](./setup.sh) and modify for your system. | ||
| 26 | 27 | ||
| 27 | ## Get Started | 28 | ## Get Started |
| 28 | 29 | ||
| @@ -33,13 +34,13 @@ Please see [Usage](./docs/det_usage.md) for training and testing with this repos | |||
| 33 | 34 | ||
| 34 | ## Benchmark and Model Zoo | 35 | ## Benchmark and Model Zoo |
| 35 | 36 | ||
| 36 | Several trained models with accuracy report is available at [Jacinto-AI-Detection Model Zoo](./docs/det_modelzoo.md) | 37 | Accuracy report of several trained models is available at the [Model Zoo](./docs/det_modelzoo.md) |
| 37 | 38 | ||
| 38 | Note: This Model Zoo is not publicly available yet - we shall make this available shortly. | ||
| 39 | 39 | ||
| 40 | ## Quantization | 40 | ## Quantization |
| 41 | 41 | ||
| 42 | This tutorial explaines how to do [Quantization Aware Training](./docs/det_quantization.md) of detection models. We also provide sample QAT models. | 42 | This tutorial explains how to do [Quantization Aware Training (QAT)](./docs/det_quantization.md) of detection models. |
| 43 | |||
| 43 | 44 | ||
| 44 | ## ONNX & Prototxt Export | 45 | ## ONNX & Prototxt Export |
| 45 | - **Export of ONNX model (.onnx) and additional meta information (.prototxt)** is supported. The .prototxt contains meta information specified in **[TIDL](https://software-dl.ti.com/jacinto7/esd/processor-sdk-rtos-jacinto7/latest/exports/docs/psdk_rtos_auto/docs/user_guide/sdk_components.html#ti-deep-learning-library-tidl)** for object detectors. | 46 | - **Export of ONNX model (.onnx) and additional meta information (.prototxt)** is supported. The .prototxt contains meta information specified in **[TIDL](https://software-dl.ti.com/jacinto7/esd/processor-sdk-rtos-jacinto7/latest/exports/docs/psdk_rtos_auto/docs/user_guide/sdk_components.html#ti-deep-learning-library-tidl)** for object detectors. |
| @@ -48,6 +49,7 @@ This tutorial explaines how to do [Quantization Aware Training](./docs/det_quant | |||
| 48 | 49 | ||
| 49 | - For more information please see [Usage](./docs/det_usage.md) | 50 | - For more information please see [Usage](./docs/det_usage.md) |
| 50 | 51 | ||
| 52 | |||
| 51 | ## Acknowledgement | 53 | ## Acknowledgement |
| 52 | 54 | ||
| 53 | This is an open source project that is contributed by researchers and engineers from various colleges and companies. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedbacks. | 55 | This is an open source project that is contributed by researchers and engineers from various colleges and companies. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedbacks. |