search

JWSoh / MZSR

Meta-Transfer Learning for Zero-Shot Super-Resolution (CVPR, 2020)
269 stars 62 forks source link

How to get kernel for the real image dataset? #14

Open omidbazgirTTU opened 4 years ago

omidbazgirTTU commented 4 years ago

Thanks for the nice work, and very well documentation.

I have some real low-resolution images without any ground-truth. I wanted to test your state-of-the-art MZSR model on that. I noticed that for testing as mention in the readme file I need "Ready for the input data (low-resolution) and corresponding kernel (kernel.mat file.)". I couldn't find any information neither in the paper nor in the repo regarding how to get the Kernel file. Could you please let me know what is the code for that? Did you use any other paper to compute the kernel? Thank you.

zerodohero commented 4 years ago

I have the same problem, and I can't use my own image to generate hyperresolution images, and I guarantee that gt is twice as much input as input. And I made the following mistakes when I was training.

Model Params: 225 K ==================== PRETRAINED MODEL Loading Succeeded ==================== ==================== Reading Checkpoints ====================

**=================== Fail to find a Checkpoint ====================

==================== No model to load ======================================* [] Training Starts

Process finished with exit code -1073741819 (0xC0000005)

liqilei commented 3 years ago

Thanks for the nice work, and very well documentation.

I have some real low-resolution images without any ground-truth. I wanted to test your state-of-the-art MZSR model on that. I noticed that for testing as mention in the readme file I need "Ready for the input data (low-resolution) and corresponding kernel (kernel.mat file.)". I couldn't find any information neither in the paper nor in the repo regarding how to get the Kernel file. Could you please let me know what is the code for that? Did you use any other paper to compute the kernel? Thank you.

Hi, you can try https://github.com/sefibk/KernelGAN to estimate the kernel.

liqilei commented 3 years ago

I have the same problem, and I can't use my own image to generate hyperresolution images, and I guarantee that gt is twice as much input as input. And I made the following mistakes when I was training.

Model Params: 225 K ==================== PRETRAINED MODEL Loading Succeeded ==================== ==================== Reading Checkpoints ====================

**=================== Fail to find a Checkpoint ====================

==================== No model to load ======================================* [] Training Starts

Process finished with exit code -1073741819 (0xC0000005)

I guess there is something wrong in the train_MZSR.tfrecord file. You may refer to MainSR to generate this file and try again.

JWSoh commented 3 years ago

We have used kernel estimation algorithm based on Pan et al. "Blind image deblurring using dark channel prior." CVPR 2016. We have slightly modified for super-resolution.

Also, after we submit the paper, we have tried the recent algorithm KernelGAN, Bell-Kligler et al. "Blind super-resolution kernel estimation using an internal-gan." NeurIPS. 2019. which yields nice results.

BassantTolba1234 commented 3 years ago

Dear Sir, Amazing work ! Congratulation!! please , I have a question.can you kindly provide me with the full path I should insert of checkpoint the trained large scale training model to be able to use it as a pre-trained to meta transfer training? I'm waiting for your reply. Thanks in advance

BassantTolba1234 commented 3 years ago

Please @omidbazgirTTU I'm facing a problem when i load the pretrained model , specially when it reads the checkpoint this is the error .. how did you kindly solve it please ??

NotFoundError (see above for traceback): Key MODEL/conv7/kernel/Adam_3 not found in checkpoint [[Node: save/RestoreV2_69 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_69/tensor_names, save/RestoreV2_69/shape_and_slices)]]

BassantTolba1234 commented 3 years ago

Please @liqilei I'm facing a problem when i load the pretrained model , specially when it reads the checkpoint this is the error .. how did you kindly solve it please ??

NotFoundError (see above for traceback): Key MODEL/conv7/kernel/Adam_3 not found in checkpoint [[Node: save/RestoreV2_69 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_69/tensor_names, save/RestoreV2_69/shape_and_slices)]]

BassantTolba1234 commented 3 years ago

Please @JWSoh I'm facing a problem when i load the pretrained model , specially when it reads the checkpoint this is the error .. how did you kindly solve it please ??

NotFoundError (see above for traceback): Key MODEL/conv7/kernel/Adam_3 not found in checkpoint [[Node: save/RestoreV2_69 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_69/tensor_names, save/RestoreV2_69/shape_and_slices)]]