search

dbpprt / u-2-net-portrait

The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."
Apache License 2.0
117 stars 14 forks source link

Train Error #16

Closed juergengunz closed 1 year ago

juergengunz commented 1 year ago

Hello,

I am getting this error when trying to run train.py - any idea what this means or how to fix it?

Start training... Traceback (most recent call last): File "train.py", line 144, in main train_one_epoch(writer, device, model, optimizer, scaler, train_dataloader, epoch, cfg) File "train.py", line 238, in train_one_epoch for x, y, metadata in metric_logger.log_every(data_loader, cfg.trainer.print_freq): File "C:\Users\Admin\Documents\Apps\test\u-2-net-portrait\lib\utils\logger.py", line 184, in log_every for obj in iterable: File "C:\Users\Admin\Documents\Apps\test\u-2-net-portrait\lib\data\dataloader.py", line 14, in iter for batch in self.loader: File "C:\Users\Admin\anaconda3\envs\mypy36env\lib\site-packages\torch\utils\data\dataloader.py", line 521, in next data = self._next_data() File "C:\Users\Admin\anaconda3\envs\mypy36env\lib\site-packages\torch\utils\data\dataloader.py", line 560, in _next_data index = self._next_index() # may raise StopIteration File "C:\Users\Admin\anaconda3\envs\mypy36env\lib\site-packages\torch\utils\data\dataloader.py", line 512, in _next_index return next(self._sampler_iter) # may raise StopIteration File "C:\Users\Admin\anaconda3\envs\mypy36env\lib\site-packages\torch\utils\data\sampler.py", line 229, in iter for idx in self.sampler: File "C:\Users\Admin\anaconda3\envs\mypy36env\lib\site-packages\torch\utils\data\sampler.py", line 189, in iter rand_tensor = torch.multinomial(self.weights, self.num_samples, self.replacement, generator=self.generator) RuntimeError: invalid multinomial distribution (sum of probabilities <= 0)

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.

juergengunz commented 1 year ago

The issue was my masks were .png but script expects .jpg.