Generating the datasets took a good few hours and training just one model took nearly the whole day.
The rest is used up generating the model. The training scripts download about 42GB worth of videos and 9GB worth of images. I then went through it again with a GeForce GTX 1050TI 4GB card and It did proceed to use the CPU but was very slow. Only to get to the final ffmpeg upscaling for it to tell me I neededĪ capability of 6.0. The way through this once with a GeForce GT710 (capability of 3.5) A CUDA enabled GPU with a capability of at least 6.0.I have not tested many other videos and I also have quite a lot to learn about SR like if I feed it different training material will I get a better result. Bear in mind that my test was upscaling from 640x360 flv file to 1920x1080 mp4. I felt on my test videos that lanczos did an ever so slightly better job. Before proceeding it is worth saying that I was not overly impressed by the result. I realise this question is pretty old now but it still comes up quite high in search results so I would like to document how I got the "sr" to work (August 2020) in case it can help someone else.
0 kommentar(er)
