Preprocess of mask
Opened this issue · 13 comments
Hi, @yingchen001
Thank you for sharing your nice work!
I have two questions about a preprocess of irregular mask dataset.
-
Did you use NVIDIA Irregular Mask Dataset: Training Set and NVIDIA Irregular Mask Dataset: Testing Set in official page, right?
-
In the above page, authors said that "please use random augmentation tricks". However, I cannot find augmentation for original masks in https://github.com/yingchen001/BAT-Fill/blob/master/data/inpaint_dataset.py#L187. In fact, I obtain a image as shown in below.
Would you tell me these answers?
Best regards.
Hi,
Thanks for your interest.
- We're using the test set of the irregular masks.
- We apply random flip on both image and masks during training, as per our codes:
if self.opt.phase == 'train' and not if_tran_sample: img = transforms.RandomHorizontalFlip()(img) img = transforms.ColorJitter(0.05, 0.05, 0.05, 0.05)(img) mask = transforms.RandomHorizontalFlip()(mask) mask = mask.filter(ImageFilter.MaxFilter(3))
Regards.
Thank you for your reply.
You mean you use the test set for training your model, right?
Yes, that's correct.
@yingchen001
您好,非常感谢您的分享,麻烦问一下,您的这个模型是将places2的数据直接作为输入的吗?我训练的时候只有这样一个显示
训练完之后只有这样两个文件。
是哪里出问题了吗?
Nope, that's all right. The file records the training iterations for continued training, it's okay to train without it.
- It will load the saved checkpoint if you want to continue training.
- As per error says, you may need to convert the tensor to CPU by using .cpu()
- The pretrained VGG model is used for training the upsampler, not the transformer.
Thanks.
cluster = torch.from_numpy(np.load('/data/vdc/yingchen.yu/project/GPT_Inpaint/kmeans_centers.npy'))
您好,我遇到一个问题,请问这个kmeans_centers.npy文件是需要自己下载,然后放到对应的路径吗
kmeans_centers
yes, please change the abs path to the downloaded kmeans path