Secant
Secant
我的数据集制作成了和REDS数据集相似的样子，但是有些地方不一样，分辨率方面我的GT是1920*1080的分辨率，bicubic是420*270；REDS是每个视频100帧，我的数据集每个视频128帧，我一共有200个视频，我像REDS那样把他们从000命名到200，然后里面是png图像的格式，现在我在那个预设的.yml文件里的某些设置可能不太对，但是我也不太清楚哪里出了问题。
# general settings name: 104_EDVR_L_x4_SR_GameDataset_600k_B4G1_valGameDataset4_103pretrain_wandb model_type: EDVRModel scale: 4 num_gpu: 1 # set num_gpu: 0 for cpu mode manual_seed: 10 # dataset and data loader settings datasets: train: name: GameDataset...
meta_info里的内容我也相对应地改了的： 000 128 (1080,1920,3) 001 128 (1080,1920,3) 002 128 (1080,1920,3) 003 128 (1080,1920,3) 004 128 (1080,1920,3) 005 128 (1080,1920,3) 006 128 (1080,1920,3) 007 128 (1080,1920,3) 008 128 (1080,1920,3) 009 128...
您好，我找出了问题，是最后多了一行空白导致读取错误 ...... 197 128 (1080,1920,3) 198 128 (1080,1920,3) 199 128 (1080,1920,3) 200 128 (1080,1920,3) （这里有一行空白忘去掉了）
您好，虽然上一个问题解决了，但是我得预设好像还是有问题，请问一下如果我用自己的这个数据集进行训练的话，dataset的type我该如何选择
Thank you for your prompt reply., the problem has been solved!! I have some other minor questions: 1. Is Sample.png a totally fake stylegan-randomly-generated picture? 2. (For further researching) I...
2. Haha, I'm just planning simply to put the result of ResNet's eigenvector into generate.py and to see what's gonna happen. By the way, I noticed that the generated sample...
Thanks a million.
Sorry, where can I put my eigenvector into generate.py instead of a random one? I tried some locations but failed.
> You can pass it to the generator: https://github.com/rosinality/style-based-gan-pytorch/blob/master/generate.py#L29 That works. Thanks 👍