runtimeerror when using other dataset?

[jingyunliang]

runtimeerror when using other dataset?

[JingyunLiang]

Could you provide the complete error log? Is there a problem in training or testing? I guess one image is less than 256x256 in your training set.

[hcleung3325]

Thanks for the reply.
I think I find the problem.
It is related to the datasets pixel boundary problem.
I will fixed the images in dataset.
Thanks.

[hcleung3325]

Also, may I ask that when I load the pretrain_G, and pretrain E,
, "path": {
"root": "superresolution" // "denoising" | "superresolution" | "dejpeg"
, "pretrained_netG": "supersolution/swinir_sr_classical_patch64_x4_l1_test/model/5000_G.pth" // path of pretrained model. We fine-tune X3/X4/X8 models from X2 model, so that G_optimizer_lr and G_scheduler_milestones can be halved to save time.
, "pretrained_netE": "supersolution/swinir_sr_classical_patch64_x4_l1_test/model/5000_E.pth" // path of pretrained model
}
However, the printed status on the terminal mentioned pretrained_netG= null pretrained_netE=null
Is that I loaded the pretrain model?
Thanks.

[hcleung3325]

Could you provide the complete error log? Is there a problem in training or testing? I guess one image is less than 256x256 in your training set.

Thanks for reply.
After I fixed the pixel problem of the image, there is another error comes out.
Do u have any idea for that?
Thanks.

data = [self.dataset[idx] for idx in possibly_batched_index]

File "/data1/anaconda3/envs/py37_pytorch1.6/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 "/data1/KAIR/data/dataset_sr.py", line 43, in getitem
img_H = util.imread_uint(H_path, self.n_channels)
File "/data1/KAIR/utils/utils_image.py", line 193, in imread_uint
if img.ndim == 2:
AttributeError: 'NoneType' object has no attribute 'ndim'

[JingyunLiang]

For 'NoneType' object has no attribute 'ndim', it's always due to that the image path in invalid.

[hcleung3325]

For 'NoneType' object has no attribute 'ndim', it's always due to that the image path in invalid.

Thanks I got it.
May I ask that when I load the pretrain_G, and pretrain E,
, "path": {
"root": "superresolution" // "denoising" | "superresolution" | "dejpeg"
, "pretrained_netG": "supersolution/swinir_sr_classical_patch64_x4_l1_test/model/5000_G.pth" // path of pretrained model. We fine-tune X3/X4/X8 models from X2 model, so that G_optimizer_lr and G_scheduler_milestones can be halved to save time.
, "pretrained_netE": "supersolution/swinir_sr_classical_patch64_x4_l1_test/model/5000_E.pth" // path of pretrained model
}
However, the printed status on the terminal mentioned pretrained_netG= null pretrained_netE=null
Is that I loaded the pretrain model?
Thanks.

[JingyunLiang]

For loading pretrained models, see #24 (comment) for a temporary solution. We will work on it later.