pytorch-semseg
pytorch-semseg copied to clipboard
meetps
Semantic Segmentation Architectures Implemented in PyTorch
Hi, I am wondering that how to train with my own dataset and mask. I have searched issues, but it seems that there was not any update for the customise...
RUNDIR: runs/fcn8s_nyuv2/11739 Traceback (most recent call last): File "/home/wangfusheng18/fengeduibifangfa/pytorch-semseg-master/train.py", line 250, in train(cfg, writer, logger) File "/home/wangfusheng18/fengeduibifangfa/pytorch-semseg-master/train.py", line 118, in train for (images, labels) in trainloader: File "/home/wangfusheng18/.conda/envs/torch0.4.1/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 336,...
hello, when I trained the pspnet, I found the ouput of this network has 2 tensors. So, the loss function cannot accept this output and lead to crash. Could you...
It seems Batchnorm module won't take a batch of size 1. You can check https://github.com/pytorch/pytorch/issues/4534 So during training if your last batch only has one element it was raise this...
I just downloaded pascal voc dataset, and pre-encoded direcotry is empty. Also in the pascal_voc_loader, the pixel mapping to class index is not there. For example, in the seg mask...
Inference time (iter 1): 1.05497 fps Inference time (iter 2): 0.38555 fps Inference time (iter 3): 0.38023 fps Inference time (iter 4): 0.38137 fps Inference time (iter 5): 0.37877 fps...
When i train the unet model，i got this error： RuntimeError: inconsistent tensor sizes at/b/wheel/pytorchsrc/torch/lib/THC/generic/THCTensorMath.cu:141 my input image size is 256*256
Hello, I'm using Mac Os and I wrote 'python train.py [-h] [--config [CONFIG]]' on terminal (mac). But it occured error: unrecognized argument. Do I have to use Window command? or...
When I trained unet in the pascal voc dataset and i set learning rate=0.001, the loss was particularly large: Iter [1833/300000] Loss: 115374464.0000 Time/Image: 0.0173 Iter [1834/300000] Loss: 22800710.0000 Time/Image:...
i try to run icnet with pascalvoc VOC2012, BUT i met this error: ``` train.py:230: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read...
