oneTaken

Very small gradients causing no weight update from your model

31

Thanks for your code. It helps me understand the BiDAF in details. However, I found the model had no performance increasing. Every epoch, the metric is always the same. And...

modify the measure.scenedet function with process bar and simpler implementation. 1. add process bar. It's help to know the status. I run the code, and long time passes, and I...

In the Rgb2Raw branch，the feature map before Mosaic is `HxWx3`，and you use this code to generate final raw output: ``` def mosaic(images): shape = images.shape red = images[:, 0, 0::2,...

python isp result different with matlab code

9

Hey, thanks for your python implementation of the isp code. I tried with the python isp code, and I found the result is really different with the matlab result. I...

why finger.png the py version psnr decrase so much?

3

As described as the title. sigma = 80: Py version psnr: ` 17.781 ` Cpp version psnr: `20.196 `

Can you provide the pretrained model?

1

The two files under the folder model is just only the `net` class file. There is no pretrained weight。 Can you provide the pretrained model to have a look on...

misalignment problem in the dataset

13

A question in the **test_Sony.py** is that, the ```scipy.io``` is really slow and ```cv2.imwrite``` is really fast. In the 8-bit saving way, do this two methods inference the finnaly PSNR...

In your paper, the **Fig 3** is very meaningful. It's very easy to find the missing parts in the corresponding error map. Can you provide the error map function? Thanks...

It's better to do something with the pretrained model.