search

PaddlePaddle / PaddleSeg

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image Matting, 3D Segmentation, etc.
https://arxiv.org/abs/2101.06175
Apache License 2.0
8.68k stars 1.68k forks source link

关于ddrnet #2742

Closed xiaodaomingye459 closed 1 year ago

xiaodaomingye459 commented 1 year ago

我在config里面只找到关于ddrnet23的配置文件， 而我想自己训练ddrnet23-slim的模型， 请问下官方有没有提供关于ddrnet23-slim的预训练模型呢？

xiaodaomingye459 commented 1 year ago

还有就是从哪里可以看到官方提供了哪些预训练模型， 有没有一个完整的目录可以查询。

haoyuying commented 1 year ago

目前我们只提供了这个模型：https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/configs/ddrnet slim产生模型可参考这个文档：https://github.com/PaddlePaddle/PaddleSeg/blob/12b008034854b95c70621f36bb67d680edc5d106/docs/slim/quant/quant_cn.md 全部模型请参考reame中的overview部分。

xiaodaomingye459 commented 1 year ago

请问提供的预训练模型是在imagenet上做的预训练吗， 如果我自己想要类似的预训练有没有类似的教程， 您提供的链接好像是模型量化的教程。

wuyefeilin commented 1 year ago

整体模型我们提供了cityscapes的预训练，没有imagenet上的预训练。

github-actions[bot] commented 1 year ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.