Crestina2001
Crestina2001
Same question here.
It seems that robert's suggestions can work, but gradOutput.data.resize_(batchSize, 1, K+1) in around line 60 should be changed to gradOutput.resize_(batchSize, 1, K + 1).
prog_bar = tqdm(enumerate(train_data_loader)) 如果是这一行卡住的话，是因为filelists/train.txt, filelists/val.txt, filelists/test.txt没配置好，导致Dataset死循环 检查Dataset.__getitem__方法，卡在while(1)里面，while(1)得到一个错误的输入直接continue...
Hi. For those wondering that how to import face_landmarks_detector, here is the code: ` BaseOptions = mp.tasks.BaseOptions FaceLandmarker = mp.tasks.vision.FaceLandmarker FaceLandmarkerOptions = mp.tasks.vision.FaceLandmarkerOptions VisionRunningMode = mp.tasks.vision.RunningMode options = FaceLandmarkerOptions( base_options=BaseOptions(model_asset_path=args.face_landmarks_detector_path),...
Having a --resize_factor seems not to work, when my videos are already of 720P.
Hi, I have the same problem, and how could I fix it?
> change the for loop in inference_gfpgan.py tomultiprocessing exp : https://github.com/FXmonkey/GFPGAN-Speed This works for me. It speeds up a lot!
1，请教下，使用自己做的LRS2数据集训练之后，训练了好几天，每一个生成的checkpoint都是一样大的 为啥checkpoints会不一样大？ 2，而且我没有发现训练日志，不知道应该选择哪个checkpoint，有什么方法吗 自己写一个logging 3，最后，感觉有点点不友好，训练时看不到还需要多长时间，我2分钟视频训练了3天都没结束 训练到了感觉差不多了就按ctrl+c结束
Hi, I am also working on the project, but cannot find an evaluation code. Do you implement the calculate_scores_real_videos.sh by yourself?
> > Hi, I am also working on the project, but cannot find an evaluation code. Do you implement the calculate_scores_real_videos.sh by yourself? > > No I didn't. Please just...