Deeplab-v3plus
Deeplab-v3plus copied to clipboard
hualin95
A higher performance pytorch implementation of DeepLab V3 Plus(DeepLab v3+)
Bumps [pillow](https://github.com/python-pillow/Pillow) from 8.1.2 to 9.3.0. Release notes Sourced from pillow's releases. 9.3.0 https://pillow.readthedocs.io/en/stable/releasenotes/9.3.0.html Changes Initialize libtiff buffer when saving #6699 [@radarhere] Limit SAMPLESPERPIXEL to avoid runtime DOS #6700 [@wiredfool]...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
Bumps [numpy](https://github.com/numpy/numpy) from 1.14.6 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...
When I run the train_voc.py,it run this issue.I don't know how to solve it Traceback (most recent call last): File "train_voc.py", line 453, in agent.main() File "train_voc.py", line 120, in...
Hi,great work and thanks for sharing your scripts. May I ask a question? I cannot reproducing your 79.19% IoU although I didn't change the configs——I use 4 GPUs with batch...
@hualin95 So I have been trying to train on cityscapes dataset and everytime the gpu crashes an show an error like `GPU is lost. Please reboot to recover the gpu`....
Thanks for your excellent work, but when I start training, found that there is no train.py. so I run train_voc.py, but there is no libs.modules and also others from libs....
Hello, thanks for your excellent work ! Do you have pre-trained weights for cityscape, how about the results ? Appreciate it if you can provide the pre-trained weights. Thanks
Thank you for your nice work! I have 2 questions, could you help me? 1. You said it's better to set batchsize=16, you mean total batchsize or each gpu batchsize?...
I see for validation on the PASCAL VOC dataset, you first train with stride 16, and then finetune with stride 8. But as I understood and experimented, original paper of...
- thanks for you code . - now i want to train the cityscapes mode ? how about this dataset result ? thanks again!
