semantic-segmentation-codebase icon indicating copy to clipboard operation
semantic-segmentation-codebase copied to clipboard
verified publisher icon YudeWang

Deeplabv3+voc does not train after loading the model

Open Carlisle-Liu opened this issue 5 years ago • 2 comments

The deeplab v3 version does not train after loading the model. It's stuck at 0% forever as shown below:

(deeplab-yude) u6617221@anaconda:~/Models/semantic-segmentation-codebase/experiment/deeplabv3+voc$ python train.py /students/u6617221/Models/semantic-segmentation-codebase/model/resnet101s-03a0f310.pth loaded. Use 6 GPU 0%| | 0/30000 [00:00<?, ?it/s]

Carlisle-Liu avatar Jan 26 '21 03:01 Carlisle-Liu

Hello, has the problem been solved? I have a similar problem. By the way, I used 4 GPUs.

xigua1025 avatar Jun 09 '21 08:06 xigua1025

I also find it very slow when training. image

zaiquanyang avatar Nov 01 '22 07:11 zaiquanyang