WindVChen

Results 160 comments of WindVChen

1. The files in different subfolders need to share the same names. 2. The program will search for the degraded images in the **degrade** subfolder. You can refer to the...

Hi there, The DRENet will leverage both degraded images and non-degraded images for training. It is recommended to have a look at the design details in our [paper](https://ieeexplore.ieee.org/document/9791363).

Yes, the Degraded function and its severity can be changed according to your needs. You can see how we determine the degraded function and its parameters in https://github.com/WindVChen/DRENet/issues/3 and https://github.com/WindVChen/DRENet/issues/4#issuecomment-1381286046....

Hi there, It is a good idea. Since the degraded function/branch does not rely on the BBOX angle, I believe it is feasible and easy to extend to the oriented...

你好呀@hotea1 , 这个问题是因为400不是32的整数倍引起的。在DRENet网络中,feature map的长宽至多会缩小到原图的1/32(见[Readme](https://github.com/WindVChen/DRENet)中的DRENet网络结构图),因此需要保证输入图像是32的整数倍。 你可以直接通过设置detect.py中的参数“--img-size”为32的整数倍来避免上述错误(例如设置为512),该设置会在你图像的边缘加入padding,因此不会改动你图像的空间分辨率(当然你也可以自行放缩图像到32的整数倍)。 此外,之前的detect.py需要做些许改动才能运行,我们更新了新的版本,请使用最新的detect.py文件。 如果觉得该方法有帮助的话,也可以给我们加:star:呀~

Hi, have you modified the argument "img-size" in the train.py, which should be set to your input image size? What else, if you use a size different with 512, you...

I have revisited the code, and found that the input image size should be even strictly (or the cat dimensions in Focus module of YOLOv5 will be inconsistent). So, you...

It seems it is caused by the missing of the matching dgimgs. You can assert the codeline ```assert dgimg is not None, 'DGImage Not Found ' + dgpath``` into line...

I'm not sure what caused the problem. Did you modify the values returned by the function "load_image(self, index)"? Or try to delete the ".cache" files under the train/val/test directories to...

It seems it is still caused by the missing of degraded images. I suggest to again check that each image has its corresponding degraded image in the train/val/test datasets.