Data set access.

[anton-starodub]

I wasn't able to pull the data. Baidu wanted me to sign up/login using phone number and I never received text from them.
Is there a chance you can upload it to dropbox or gdrive?

[devrosx]

used this website with url and it works without registration...
https://oneleaf.icu

[253719358321]

I was wondering, is model.py a network module? But this is not the same as the network module described in the paper

[liulanxi]

Is there an additional loss function(TV loss)? TV loss seem does not appear in the original paper.

[GuangwuOfLongCity]

I want to know how to set batch_size. The error CUDA out of memory is always exists.
Could you help me? @leftthomas Thank you very much!

[WenBingo]

UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
xml_shape = ' shape="%s"' % make_valid_xml_value("%s" % str(len(v)))

Could you help me?

[SamehOmri]

when excute testbenchmark.py
File "/content/drive/MyDrive/SRGAN/test_benchmark.py", line 33, in
test_set = TestDatasetFromFolder('data/test/', upscale_factor=UPSCALE_FACTOR)
File "/content/drive/MyDrive/SRGAN/data_utils.py", line 85, in init
self.lr_filenames = [join(self.lr_path, x) for x in listdir(self.lr_path) if is_image_file(x)]
FileNotFoundError: [Errno 2] No such file or directory: 'data/test//SRF_2/data/'

[dawn-moqing]

我想知道如何设置 .错误始终存在。您能帮我吗？ 谢谢！batch_size``CUDA out of memory

File "C:\Users\33204.conda\envs\SRGAN\lib\site-packages\torch\nn\functional.py", line 2512, in batch_norm
return torch.batch_norm(
torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 676.00 MiB. GPU 0 has a total capacity of 4.00 GiB of which 0 bytes is free. Of the allocated memory 18.52 GiB is allocated by PyTorch, and 1.17 MiB is reserved by PyTorch but unallocated.

[253719358321]

将batch_size设置的小一点，或者换一张显存大一点的显卡

…

------------------ 原始邮件 ------------------ 发件人: "leftthomas/SRGAN" ***@***.***>; 发送时间: 2024年8月27日(星期二) 晚上8:02 ***@***.***>; ***@***.******@***.***>; 主题: Re: [leftthomas/SRGAN] Data set access. (Issue #125) 我想知道如何设置 .错误始终存在。您能帮我吗？ 谢谢！batch_size``CUDA out of memory File "C:\Users\33204.conda\envs\SRGAN\lib\site-packages\torch\nn\functional.py", line 2512, in batch_norm return torch.batch_norm( torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 676.00 MiB. GPU 0 has a total capacity of 4.00 GiB of which 0 bytes is free. Of the allocated memory 18.52 GiB is allocated by PyTorch, and 1.17 MiB is reserved by PyTorch but unallocated. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: ***@***.***>

[dawn-moqing]

将batch_size设置的小一点，或者换一张显存大一点的显卡
…
------------------ 原始邮件 ------------------ 发件人： “leftthomas/SRGAN” @.>; 发送时间： 2024年8月27日(星期二) 晚上8:02 @.>; @.@.>; 主题： 回复：[leftthomas/SRGAN] 数据集访问。（问题 #125） 我想知道如何设置 .错误始终存在。谢谢！batch_size''CUDA 内存不足 文件“C：\Users\33204.conda\envs\SRGAN\lib\site-packages\torch\nn\functional.py”，第 2512 行，batch_norm 返回 torch.batch_norm（ 炬。OutOfMemoryError：CUDA 内存不足。尝试分配 676.00 MiB。GPU 0 的总容量为 4.00 GiB，其中 0 字节是空闲的。在分配的内存中，18.52 GiB 由 PyTorch 分配，1.17 MiB 由 PyTorch 保留但未分配。 — 直接回复此电子邮件，在 GitHub 上查看，或取消订阅。 您收到此消息是因为您发表了评论。消息 ID：@.***>
我在运行test-image时遇到这个问题，没有batch-size这个参数