search

meetps / pytorch-semseg

Semantic Segmentation Architectures Implemented in PyTorch
https://meetshah.dev/semantic-segmentation/deep-learning/pytorch/visdom/2017/06/01/semantic-segmentation-over-the-years.html
MIT License
3.38k stars 799 forks source link

AttributeError: module 'torchvision.transforms.functional' has no attribute 'affine' #230

Open yaoyz96 opened 4 years ago

yaoyz96 commented 4 years ago

when I run python train.py --config configs/pspnet_pascal_yml, give me this error:

Traceback (most recent call last): File "train.py", line 229, in train(cfg, writer, logger) File "train.py", line 118, in train for (images, labels) in trainloader: File "/data/zyy/usr/local/anaconda3/envs/pytorch-semseg/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 637, in next return self._process_next_batch(batch) File "/data/zyy/usr/local/anaconda3/envs/pytorch-semseg/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 658, in _process_next_batch raise batch.exc_type(batch.exc_msg) AttributeError: Traceback (most recent call last): File "/data/zyy/usr/local/anaconda3/envs/pytorch-semseg/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 138, in _worker_loop samples = collate_fn([dataset[i] for i in batch_indices]) File "/data/zyy/usr/local/anaconda3/envs/pytorch-semseg/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 138, in samples = collate_fn([dataset[i] for i in batch_indices]) File "/data/zyy/code/pytorch-semseg-master/ptsemseg/loader/pascal_voc_loader.py", line 92, in getitem im, lbl = self.augmentations(im, lbl) File "/data/zyy/code/pytorch-semseg-master/ptsemseg/augmentations/augmentations.py", line 23, in call img, mask = a(img, mask) File "/data/zyy/code/pytorch-semseg-master/ptsemseg/augmentations/augmentations.py", line 207, in call tf.affine( AttributeError: module 'torchvision.transforms.functional' has no attribute 'affine'

AttributeError: module 'torchvision.transforms.functional' has no attribute 'affine' I have tried torch==0.4.1 and ==1.0, torchvision version==0.2.0, but can't fix it. can anyone help me to solve this probelm?