d21682da79
* upload original backbone and configs * ConvNext Refactor * ConvNext Refactor * convnext customization refactor with mmseg style * convnext customization refactor with mmseg style * add ade20k_640x640.py * upload files for training * delete dist_optimizer_hook and remove layer_decay_optimizer_constructor * check max(out_indices) < num_stages * add unittest * fix lint error * use MMClassification backbone * fix bugs in base_1k * add mmcls in requirements/mminstall.txt * add mmcls in requirements/mminstall.txt * fix drop_path_rate and layer_scale_init_value * use logger.info instead of print * add mmcls in runtime.txt * fix f string && delete * add doctring in LearningRateDecayOptimizerConstructor and fix mmcls version in requirements * fix typo in LearningRateDecayOptimizerConstructor * use ConvNext models in unit test for LearningRateDecayOptimizerConstructor * add unit test * fix typo * fix typo * add layer_wise and fix redundant backbone.downsample_norm in it * fix unit test * give a ground truth lr_scale and weight_decay * upload models and readme * delete 'backbone.stem_norm' and 'backbone.downsample_norm' in get_num_layer() * fix unit test and use mmcls url * update md2yml.py and metafile * fix typo
Kneron AI Training/Deployment Platform (mmsegmentation-based)
Introduction
kneron-mmsegmentation is a platform built upon the well-known mmsegmentation for mmsegmentation. If you are looking for original mmsegmentation document, please visit mmsegmentation docs for detailed mmsegmentation usage.
In this repository, we provide an end-to-end training/deployment flow to realize on Kneron's AI accelerators:
- Training/Evalulation:
- Modified model configuration file and verified for Kneron hardware platform
- Please see Overview of Benchmark and Model Zoo for Kneron-Verified model list
- Converting to ONNX:
- tools/pytorch2onnx_kneron.py (beta)
- Export optimized and Kneron-toolchain supported onnx
- Automatically modify model for arbitrary data normalization preprocess
- Evaluation
- tools/test_kneron.py (beta)
- Evaluate the model with pytorch checkpoint, onnx, and kneron-nef
- Testing
- inference_kn (beta)
- Verify the converted NEF model on Kneron USB accelerator with this API
- Converting Kneron-NEF: (toolchain feature)
- Convert the trained pytorch model to Kneron-NEF model, which could be used on Kneron hardware platform.
License
This project is released under the Apache 2.0 license.
Changelog
N/A
Overview of Benchmark and Kneron Model Zoo
| Backbone | Crop Size | Mem (GB) | mIoU | Config | Download |
|---|---|---|---|---|---|
| STDC 1 | 512x1024 | 7.15 | 69.29 | config | model |
NOTE: The performance may slightly differ from the original implementation since the input size is smaller.
Installation
- Please refer to the Step 1 of docs_kneron/stdc_step_by_step.md#step-1-environment for installation.
- Please refer to Kneron PLUS - Python: Installation for the environment setup for Kneron USB accelerator.
Getting Started
Tutorial - Kneron Edition
- STDC-Seg: Step-By-Step: A tutorial for users to get started easily. To see detailed documents, please see below.
Documents - Kneron Edition
- [Kneron ONNX Export] (under development)
- [Kneron Inference] (under development)
- Kneron Toolchain Step-By-Step (YOLOv3)
- Kneron Toolchain Manual
Original mmsegmentation Documents
- Original mmsegmentation getting started: It is recommended to read the original mmsegmentation getting started documents for other mmsegmentation operations.
- Original mmsegmentation readthedoc: Original mmsegmentation documents.
Contributing
kneron-mmsegmentation a platform built upon OpenMMLab-mmsegmentation
-
For issues regarding to the original mmsegmentation: We appreciate all contributions to improve OpenMMLab-mmsegmentation. Ongoing projects can be found in out GitHub Projects. Welcome community users to participate in these projects. Please refer to CONTRIBUTING.md for the contributing guideline.
-
For issues regarding to this repository kneron-mmsegmentation: Welcome to leave the comment or submit pull requests here to improve kneron-mmsegmentation
Related Projects
- kneron-mmdetection: Kneron training/deployment platform on OpenMMLab - mmdetection object detection toolbox