pytorch-deeplab-xception

pytorch-deeplab-xception copied to clipboard

Exception: No files for split=[train] found in /dataset/cityscapes/leftImg8bit/train

1

zhujiesuper

In [here](https://github.com/jfzhang95/pytorch-deeplab-xception/blob/9135e104a7a51ea9effa9c6676a2fcffe6a6a2e6/dataloaders/datasets/cityscapes.py#L26), valid classes and class names do not match correctly. The class 7 will be 'unlabelled'. You may delete 'unlabelled' in class_names or add 0 to valid_classes **1. delete...

aspenstarss

I want to use a pre-trained model to predict pictures

xiaozhen18239228065

clownrat6

low miou when backbone ie resnet

1

han666888999

more than 3 channels

1

Hello, I wonder if the deeplab can be made to work on input data with more than 3 channels. Thanks, AS

dialuser

low mIOU in train with coco and ResNet as backbone

3

hi, thank you for your code, I trained the network use coco dataset and ResNet as backbone with 40 epoches, the problem is that Val mIOUs are same value and...

zwtburger

how to train date with 10 classes

3

sporterman

question about the training details

4

I have tried to train model with the scripts "train_voc.sh". however the best mIoU only achieved 73%, and it overfitting suddenly after 15 epoch, which will not happen without using...

SaberSong

I changed the backbone. in train.py to xception, and set the data set path in mapath. Nothing else was changed

kungkook