pytorch-deeplab-xception
pytorch-deeplab-xception copied to clipboard
DeepLab v3+ model in PyTorch. Support different backbones.
with open(os.path.join(os.path.join(_splits_dir, splt + '.txt')), "r") as f: FileNotFoundError: [Errno 2] No such file or directory: 'D:/SegNet/me/deeplab/deeplab/dataloader/datasets/VOC2012/ImageSets\\Segmentation\\train.txt'
 set backbone => xception i think the issue is wrong path...... i want to know how to load this program
I am training my own dataset with 2 classes. Got error : "CUDA error: device-side assert triggered." When I tried to run with CPU, got the error : "IndexError: Target...
Hello, I want to train my datasets. However, when I try to run the code, the error occurs as follows: `Namespace(backbone='resnet', base_size=513, batch_size=8, checkname='deeplab-resnet', crop_size=513, cuda=True, dataset='pascal', epochs=50, eval_interval=1, freeze_bn=False,...
Should the focal loss not be applied per pixel? The reduction occurs when computing the crossentropy loss but shouldn't it occur at the very end? criterion = nn.CrossEntropyLoss(weight=self.weight, ignore_index=self.ignore_index, size_average=self.size_average)...
hi, i recently use the code to train my own dataset. and i found something strange, that is on tensorboard, my val loss is always lower then train loss. however...
hi, recently i use my own dataset and run Deeplab V3+, but i got the error. i think this is about the classes but i sure that my classes is...
i want to use deeplabv3 to simultaneously output the semantic segmentation and depth estimation. Do you guys have tried this or have any ideas for this task? Thank you in...
RuntimeError: CUDA error: device-side assert triggered