thuyngch / Human-Segmentation-PyTorch

Human segmentation models, training/inference code, and trained weights, implemented in PyTorch

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

error after 1 epoch

853498747 opened this issue · comments

when i run train.py unet_config
after trained 1 epoch,error shows:

Traceback
train.py line 101
trainer.train()
base_trainer.py line95
result = self.train_epoch(epoch)
trainer/trainer.py line98
self.writer_train.add_image('train/output',make_grid(.....))
torchvision/utils.py ,line66, in make_grid
norm_range(tensor,range)
torchvision/utils.py ,line60, in norm_range
norm_ip(t,t.min,max=max)
torchvision/utils.py ,line53, in norm_ip
img.clamp_(argument 'min' must be Number ,not tensor)

can you help me ,my own dataset input is rgb ,mask is 1 channel (0,1)

It seems you customized the trainer.py.
Could you paste the trainer.py file here so that I can see what should be fixed?

I have not change anything in trainer.py. I just change the picture path config_UNet.json.
My label(mask) picture is one channel (0,1),shoud i make some changes?

Hello @853498747, did you install the same version of PyTorch?
Which is your version of PyTorch?