PUT
PUT copied to clipboard
liuqk3
Paper 'Reduce Information Loss in Transformers for Pluralistic Image Inpainting' in CVPR2022
推理问题
您好，我在使用命令：python scripts/inference.py --name transformer_mural --func inference_complet_sample_in_feature_for_evaluation --gpu 0 --batch_size 2 修复单个图像时，出现如下问题： 输入带有掩码的图像： 修复的图像：
Dear author, Thanks for sharing the code. I am greatly interested in your work. I have a question for you and would like your reply. In P-VQVAE, the masked and...
Hello, Thanks for the excellent code. I face a problem with the inference. When I run the below code for image inpainting with provided transformer model: ‘python scripts/inference_inpainting.py --func inference_inpainting...
About 推理
 这行代码输出图片没问题，检查了原图和mask图输出都没问题。 但为什么？  最终的conpleted图和原图不相干？有点困惑 原图：  mask：  补全图： 
推理遇到问题
作者您好，我使用我的训练集进行模型训练一切正常，但在测试的时候遇到了问题。 我的任务和传统的修复有点差别，首先这是我的输入图片：  这个是mask：  我的意图就是用我的mask能恰好盖住我原始图上的空洞区域，然后进行修复。 但是遇到了问题，发现推理后的图片。并没有识别到我的mask区域，
Hi, Thanks for the excellent code, when I inference the pictures, My program output is： **KeyError: 'relative_path'** Then I found "relative_path" is a key of "data_i", but when I print...
Hello, I'm very interested in your article. Thank you for your great content. I encountered the following issue while running it. Could you please provide some guidance? Thank you. 
Hi, Thanks for your contribution,but I'm confused about the inference. I must run the Pvqvae inference first, `python scripts/inference.py --name OUTPUT/pvqvae_exp_name/checkpoint/last.pth --func inference_reconstruction --gpu 0 --batch_size 8` then run the...
