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.

Thanks for your code first! I‘d like to ask the input and out put, which puzzled me for a long time.

1. Do you pre-process your input image? such as normalization.
2. About the output scale. For instance, if the input image is 25 x 25, then i'll finally get 100 x 100 output only in Y channel. If i want to visualize the output, the Cb and Cr channel need to be concatenate with output, but Cb and Cr channel of input LR is 25 x 25. I guess you use the bicubic interpolation to resize the Cb Cr to 100 x 100, is that correct? I am a green hand in DL and CV, so maybe some question may stupid. I'll very appreciate if you can solve my problem. Thank you!

Hi: thanks for sharing your impressive job, I want to evaluate perfermance in test.py ,I have downloaded your shared model , I encounter a error"No module named SR_DenseNet",but I can't find this class in this repo,can you add it ?thanks very much

the paper said:

Figure 2. The structure of one DenseNet block. Each block consists of 8 convolution layers. The growth rate is set to 16 and the output of each block has 128 feature maps.

It seems outChannels is from 16 to 128 in each dense block. denseblock1: 16 -> 128(16 x 8) denseblock2: 16 -> 128(16 x 8) ... ... denseblock8: 16 -> 128(16 x 8)

but SRDenseNet-pytorch, the outChannels seems from (1 x 16) to (64 x 16), I think your model is different, and much bigger.

flake8 testing of https://github.com/wxywhu/SRDenseNet-pytorch on Python 3.6.3

$ flake8 . --count --select=E901,E999,F821,F822,F823 --show-source --statistics

./train.py:131:39: F821 undefined name 'testing_data_loader'
    for iteration, batch in enumerate(testing_data_loader,1):
                                      ^
./train.py:142:63: F821 undefined name 'testing_data_loader'
            print("({}/{}):psnr:{:.8f}".format(iteration, len(testing_data_loader),psnr))
                                                              ^
./train.py:143:13: F821 undefined name 'writer'
            writer.add_scalar('psnr', psnr, (epoch-1)* 469 +iteration)
            ^
./train.py:145:13: F821 undefined name 'tf'
            tf.summary.scalar('psnr', psnr)
            ^
./train.py:146:18: F821 undefined name 'tf'
            op = tf.summary.merge_all()
                 ^
./train.py:147:27: F821 undefined name 'sess'
            summary_str = sess.run(op)
                          ^
./train.py:150:61: F821 undefined name 'testing_data_loader'
    print("===> Avg. PSNR: {:.8f} dB".format(avg_psnr / len(testing_data_loader)))
                                                            ^
7     F821 undefined name 'testing_data_loader'
7

I cannot download your pretrained model from baidu.

Because I have not baidu account.

Could I get an alternative link for download your pretrained model?

Thank you.

Why use your code to make the H5 file in MATLAB, there will be the following error: TypeError: h5py objects cannot be pickled. What could be the reason? Looking forward to your answer

Does the code you implement have the same network structure as the item C in Fig. 1 suggested by the author of the paper? If so, may I ask what the meaning of Densely Skip Connection in the picture is?

I download the pretrained model and test it. Excellent work! I

find the scale factor in the SRDensnet model is 4. what can I do if I want to use 2 or other scale factor ? Thank you for your reply !!!