ICNet-pytorch icon indicating copy to clipboard operation
ICNet-pytorch copied to clipboard

ICNet implemented by pytorch, for real-time semantic segmentation on high-resolution images, mIOU=71.0 on cityscapes, single inference time is 19ms, FPS is 52.6.

Results 12 ICNet-pytorch issues
Sort by recently updated
recently updated
newest added

hi, the download link of pretrained model seems to be invalid , could you provide a new link for us to use the pretrained model, thanks a lot!

您好,您在cityscape上训练好的模型的链接好像挂掉了 您看方便重新上传一下嘛,万分感谢

Bumps [numpy](https://github.com/numpy/numpy) from 1.17.0 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...

dependencies

Thanks for Amazing code . When reproduce your mIOU encounter some problem: 1-when Achieving 71 mIOU, do you train from imageNet pretrain model? 1- Can not loading pretrain model from...

when i run train.py,it shows this problem suddenly.what should i do?

After training with CityScapes data, what should I change if I want to use my own data images to test the effect

sir, have you ever tried ResNet101-2a57e44d.pth(or other pth based on ResNet101)? seems like it is not suitable for this mode. Also this url "https://hangzh.s3.amazonaws.com/" is invalid, we can't downloading the...

Bumps [pillow](https://github.com/python-pillow/Pillow) from 6.0.0 to 9.0.1. Release notes Sourced from pillow's releases. 9.0.1 https://pillow.readthedocs.io/en/stable/releasenotes/9.0.1.html Changes In show_file, use os.remove to remove temporary images. CVE-2022-24303 #6010 [@​radarhere, @​hugovk] Restrict builtins within...

dependencies

how to train my own dataset,I neeed ,What parameters do I need to modify