jkhu29 / deblurring-by-realistic-blurring

A PyTorch implementation of the "Deblurring by Realistic Blurring", unofficially

Hi there 👋

I'm JiaKui Hu, a Ph.D Student in PKU, MILab.

🔭 I’m currently working on

• Medical Image Processing, like SIM
• Spike Neural Network

🌱 I’m currently interested in

• Super Resolution imaging
• Network architecture design
• AI System

I have another account dedicated to the work of the open source community, like TVM, OneFlow, ... --> hhhfccz

deblurring-by-realistic-blurring's Issues

关于在评论区提到的更新一事

您好，请问您这个项目算作完成了吗？如果还有哪些需要注意或未完成的地方，可以告知一下吗？

Question!

Hi. I have a question
There is no dataset_make.py file in the dataset make folder, only tfrecord_make.py, I wonder how to use it.

TypeError: tensor is not a torch image.

Questions please!

Hi, thanks for your contribution.
I have several questions:

1. Has the project achieved the accuracy of the paper? You use a cyclegan to produce the blur data, but the paper not use the cyclegan.
2. What datasets are used for training? The training script implies that the train dataset has a length of 44185.
3. The architechture of vgg19 used by the discriminator seems not right in the codes. And the last layer feature of vgg16 is not used in perceptual loss, which is a bit difference from other projects. Why?

I am looking forward to your reply.

Hello. I ask you something about value error

I performed training after converting tfrecord type data, and a problem occurred in the process of checking the deblur effect of a single image through "demo.py".

I used the "model.png" image in the existing folder ./imge as the input image, and the following value error occurred. Can you give me some advice on how to solve it?

Traceback (most recent call last):
  File "./demo.py", line 26, in <module>
    img_yiq[..., 0] = g
ValueError: could not broadcast input array from shape (398,886) into shape (397,885)

The code I used is below.

import cv2
import torch
from skimage.color import rgb2yiq, yiq2rgb
import utils
from model import *

bgan = BlurGAN_G().cuda() 
bgan_state_dict = torch.load("./bgan_pretrain.pth")
bgan.load_state_dict(bgan_state_dict)
bgan.eval()

img = cv2.imread("img/model.png")
img_yiq = rgb2yiq(img)
img = torch.from_numpy(img.transpose(2, 0, 1)).unsqueeze(0).float().to("cuda")
n, c, h, w = img.shape
img_noise = utils.concat_noise(img, (4, h, w), img.size()[0])
img_bgan = bgan(img_noise)[0].detach().cpu().numpy()
g = utils.lum(img_bgan)
img_yiq[..., 0] = g
img_blur = yiq2rgb(img_yiq)

cv2.imwrite("img/model_blur.png", img_blur)

About Dataset

Thank you very much for opening the train code of this article. I have a set of clear and blur data of unpaired. How can I make a tf.record file that the code needs?

复现精度

请问同学复现到了论文提到的精度吗？

代码环境搭建问题

同学你好，我也最近看了这篇paper，可我不知道官方的代码怎么才能运行……能否告知下环境搭建的要求与代码运行的步骤啊？万分感谢了。