problem in training

[meroluo]

Thank you for you wonderful work! I want to train a model on my own dataset, but I meet a problem in the beginning of training, the error is described as below:

===> Setting GPU
=> loading model 'model_0.0001_epoch_60.pth'
/home/weihq/anaconda3/lib/python3.6/site-packages/torch/serialization.py:368: SourceChangeWarning: source code of class 'torch.nn.parallel.data_parallel.DataParallel' has changed. you can retrieve the original source code by accessing the object's source attribute or set torch.nn.Module.dump_patches = True and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
Traceback (most recent call last):
File "train.py", line 89, in
weights = torch.load(opt.pretrained)
File "/home/weihq/anaconda3/lib/python3.6/site-packages/torch/serialization.py", line 304, in load
return _load(f, map_location, pickle_module)
File "/home/weihq/anaconda3/lib/python3.6/site-packages/torch/serialization.py", line 470, in _load
result = unpickler.load()
UnicodeDecodeError: 'ascii' codec can't decode byte 0xc3 in position 918: ordinal not in range(128)

It seems that this error is caused by the encode-decode, but I can't find a effective solution in the webside. hoping you can give me some suggestions. I am Sincerely grateful to your reading.

[wxywhu]

It seems that the model saved by PYTHON2 is incompatible with PYTHON3. If you want to the pre-trained model, maybe you could change your version of PYTHON. @meroluo

[meroluo]

Thank you!! I will try python2 later。

[meroluo]

Sorry to bother you again! I have change the version of python to python27,but there seems to have problems with the dataset. I check the generation of my own dataset, but can't find the cause, here are the error description:
(py2) luomeilu@Ubuntu:~/superresolution/SRDenseNet-pytorch-master/SRDenseNet-pytorch-master$ python train.py
Namespace(batchSize=64, cuda=False, lr=0.0001, nEpochs=300, pretrained='model_0.0001_epoch_60.pth', resume='', start_epoch=1, step=30, testbatchSize=64, threads=1)
('Random Seed: ', 3018)
===> Loading datasets
Traceback (most recent call last):
File "train.py", line 55, in
training_data_loader = DataLoader(dataset=train_set, num_workers=opt.threads, batch_size=opt.batchSize, shuffle=True)
File "/home/luomeilu/anaconda3/envs/py2/lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 802, in init
sampler = RandomSampler(dataset)
File "/home/luomeilu/anaconda3/envs/py2/lib/python2.7/site-packages/torch/utils/data/sampler.py", line 60, in init
self.num_samples = len(self.data_source)
File "/home/luomeilu/superresolution/SRDenseNet-pytorch-master/SRDenseNet-pytorch-master/dataset.py", line 22, in len
return self.data.shape[0]
AttributeError: 'NoneType' object has no attribute 'shape'

I make my own dataset through generate_train.m, can you give me some suggestions?

[wxywhu]

@meroluo How did you process your dataset? Which format did your data save?

[meroluo]

@meroluo How did you process your dataset? Which format did your data save?

I down sample HR images with bicubic operation and save images as '.png' format.

[wxywhu]

@meroluo There might be something wrong with your method that you used to read the image, such as PIL or opencv.