ychfan / wdsr Goto Github PK

After enter python trainer.py --dataset div2k --eval_datasets div2k set5 bsds100 urban100 --model wdsr --scale 2 --job_dir ./wdsr_x2 --eval_only.I meet the following error:
Traceback (most recent call last):
File "trainer.py", line 121, in
'datasets.' + args.dataset if args.dataset else 'datasets')
File "/anaconda3/envs/pytorch/lib/python3.7/importlib/init.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "", line 1006, in _gcd_import
File "", line 983, in _find_and_load
File "", line 967, in _find_and_load_unlocked
File "", line 677, in _load_unlocked
File "", line 728, in exec_module
File "", line 219, in _call_with_frames_removed
File "/project/wdsr/datasets/div2k.py", line 4, in
import datasets._isr
File "/project/wdsr/datasets/_isr.py", line 15, in
from common.images import imresize
File "/project/wdsr/common/images.py", line 1, in
from third_party.matlab_imresize.imresize import imresize
ModuleNotFoundError: No module named 'third_party.matlab_imresize.imresize'

So i try to find the function 'imresize' under the file 'third_party.matlab_imresize',but i can't find it.

Error Log:

Traceback (most recent call last):
File "trainer.py", line 272, in
train(epoch)
File "trainer.py", line 216, in train
for batch_idx, (data, target) in enumerate(train_data_loader):
File "/home/lbz/anaconda3/envs/ACV/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 363, in next
data = self._next_data()
File "/home/lbz/anaconda3/envs/ACV/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 989, in _next_data
return self._process_data(data)
File "/home/lbz/anaconda3/envs/ACV/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1014, in _process_data
data.reraise()
File "/home/lbz/anaconda3/envs/ACV/lib/python3.7/site-packages/torch/_utils.py", line 395, in reraise
raise self.exc_type(msg)
KeyError: Caught KeyError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/lbz/anaconda3/envs/ACV/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 185, in _worker_loop
data = fetcher.fetch(index)
File "/home/lbz/anaconda3/envs/ACV/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/lbz/anaconda3/envs/ACV/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/lbz/ACV/wdsr/datasets/_isr.py", line 66, in getitem
lr_image, hr_image = self._load_item(index)
File "/home/lbz/ACV/wdsr/datasets/_isr.py", line 159, in _load_item
lr_image = self.lr_cache_file.get(self.lr_files[index][0])
File "/home/lbz/ACV/wdsr/common/io.py", line 50, in get
return self.file[key]
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "/home/lbz/anaconda3/envs/ACV/lib/python3.7/site-packages/h5py/_hl/group.py", line 288, in getitem
oid = h5o.open(self.id, self._e(name), lapl=self._lapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5o.pyx", line 190, in h5py.h5o.open
KeyError: "Unable to open object (object '0362.png' doesn't exist)"

wdsr_x2.zip
wdsr_x3.zip
wdsr_x4.zip

Hello,
MSU Graphics & Media Lab Video Group has recently launched Video Super Resolution Benchmark.
We provide a comprehensive comparison of a variety of different VSR models.
You can see our current results: MSU VSR Benchmark.
If you are interested in participating, you can add your algorithm, following the submission steps.
You can read about MSU Graphics & Media Lab Video Group here and here.

Hi,

I am facing issues installing the dependencies and getting the trainer to work.

I am unable to install the apex with legacy-install-failure error. Is there any workaround?

As your example says:
python trainer.py --dataset div2k --eval_datasets div2k set5 bsds100 urban100 --model wdsr --scale 2 --job_dir ./wdsr_x2 --eval_only

Interestingly, the trainer.py code does not contain the scale parameter. So how can I super resolve an image to 2-3-4x size and get metrics from the super-resolved image?