DeepLabv3.pytorch issues

Error with main.py

11

main.py --train --exp lr7e-3 --epochs 50 --base_lr 0.007 raise ValueError('Expected more than 1 value per channel when training, got input size {}'.format(size)) ValueError: Expected more than 1 value per channel...

chituma110

Pre-trained ResNet Models

1

Hello, Is it possible for you to provide Pre-trained ResNet-18/34/50/101 model with GroupNormalization+WeightStandardization? Thank you.

YashRunwal

Did you try to train it from sractch? Any recommendations for hyperparams?

1

Hi, thank you for your work, did you try to train it from scratch? Any recommendations for hyperparams? Thanks in advance!

diff7

Very high loss on using BCELoss

2

Hi, I wanted to try your code on SWIMSEG dataset. It has only two classes- cloud and sky (background). I got IoU of 80%. But I wanted to BCELoss instead...

prk-vinay

IOU error

4

Thank you so much for sharing! But maybe I found an error in utils.py. When computing IOU, you filtered the pred where mask == 0. It will make the IOU...

cvchanghao

Solve memory problems during evaluation by not tracking gradients

This solves https://github.com/chenxi116/DeepLabv3.pytorch/issues/14

Parskatt

RuntimeError: CUDA error: out of memory

1

This is problem feedback： Traceback (most recent call last): File "main.py", line 188, in main() File "main.py", line 167, in main outputs = model(inputs.unsqueeze(0)) File "/home/zjh/anaconda3/envs/psmnet/lib/python3.7/site-packages/torch/nn/modules/module.py", line 477, in __call__...

2679622694