CarbonPool

I tried to extract pdf media data, and it kept showing errors. I can't make github well formatted code text, I have to demonstrate the code in the image. 

最新版的360安全浏览器（内核webkit63）极速模式，访问压缩后的字体字体的宽度非常大，在chrome下正常，不压缩状态都是正常的，测试地址：http://108.160.143.50/fonts

Help with training model for noise reduction of darker area lines

1

For most of the darker images similar to this, I have tried all three-level noise reduction models, and their lines are smeared. What training set is suitable to help preserve...

Noise reduction after zooming in can not eliminate some noise

4

Purpose: The image is enlarged to 2k, and the details are preserved as much as possible Experiment: first zoom in the picture to a higher resolution using low-level noise reduction,...

How to convert a cunet model in .t7 format to a caffe model

9

With the help of waifu2x-caffe, I want to use the trained cunet model on other platforms. I saw make_cnet.py, but I didn’t understand the processing method, how to convert a...

Will the image size of the training resource affect the training result?

1

I noticed that my largest image size is 4096x2621. When the model training is completed, the model file is several hundred MB, but the default pre-trained model cunet model file...

Noise reduction produces more color banding

4

I captured some pixels. The original image:  UpPhoto DeNoise 3: 

Does model training exist in an additive manner

9

For the same model, some additional images are added, an image list is generated, and then image data is generated for training. Does the model remember the image data of...

How to implement layer scaling in krkrz kag?

1

In krkrz, there is no action tag, how to achieve excessive scaling of a layer?

I tried to train the upresnet10 model. I want to export it as a caffe model. On the gui, it is used by waifux2x-caffe. I tried to run `py .\convert_models.py`,...