iduta/pyconvsegnet

Semantic Segmentation PyTorch code for our paper: Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition (https://arxiv.org/pdf/2006.11538.pdf)

pyconvsegnet's Issues

Where to get validation.txt file in ADE20K dataset?

RuntimeError: Image list file do not exist: /raid/data/datasets/semanticSegmentation/ade20k/list/validation.txt

To solve this error I need validation.txt file from ADE20K dataset. I have tried a lot to find it but unable to find this file.

Please help me to get this file.

Thanks,
Bhavika

ModuleNotFoundError

from util import dataset, transform, config

ModuleNotFoundError: No module named 'util'

no ade20k_pyvonvsegnet152_pyvonvsegnet.yaml

Thank you for your sharing.
Could you please share your ade20k_pyvonvsegnet152_pyvonvsegnet.yaml, thers is only ade20k_pyvonvsegnet50_pyvonvsegnet.yaml in the config/ade20k.
Thank you very much.

Getting Error while prediction?

hi @iduta
Thanks for sharing the code.

When I run the test.py file, I got the following error. Please help me to solve this error.

`[2020-07-23 17:07:58,745 INFO test.py line 62 23777] => creating model ...

[2020-07-23 17:07:58,745 INFO test.py line 63 23777] Classes: 150
Totally 1 samples in val set.
Starting Checking image&label pair val list...
Checking image&label pair val list done!
Load pretrained model: exp/PyConvADE20kModels/ade20k_pyconvresnet152_pyconvsegnet.pth
Traceback (most recent call last):
File "test.py", line 269, in
main()
File "test.py", line 95, in main
backbone_net=args.backbone_net)
File "/home/pyconvsegnet/model/pyconvsegnet.py", line 163, in init
convert_bn=BatchNorm)
File "/home/pyconvsegnet/model/build_backbone_layers.py", line 62, in build_backbone_layers
backbone.load_state_dict(torch.load(pretrained), strict=True)
File "/home/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 847, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for PyConvResNet:
Missing key(s) in state_dict: "conv1.weight", "bn1.weight", "bn1.bias", "bn1.running_mean", "bn1.running_var", "fc.weight", "fc.bias".
`