Global-Flow-Local-Attention
Global-Flow-Local-Attention copied to clipboard
RenYurui
The source code for paper "Deep Image Spatial Transformation for Person Image Generation"
As the title says, I've tried many times, initially thinking the problem was the setting of setup.py, but it still doesn't work
train_A
I'm having hard time to run train.py . I keep having the same error : Assert os.path.isdir(dir),";%s is not a valid directory"; % dir AssertionError: ./dataset/danceFashion_anoo/train_256/train_256/train_A is not a valid...
Hi, The command provided ``` python demo.py --name=face_checkpoints --model=face --attn_layer=2,3 --kernel_size=2=5,3=3 --gpu_id=0 --dataset_mode=face --dataroot=./dataset/FaceForensics --results_dir=./demo_results/face ``` Seems to dump the source validation frames and extracted edges. However, how do I...
Hi,I was going through your repository and paper,and I would like to try it on my own dataset and task. The task is to transform a source person image to...
Excuse, when I cd ./model/networks/resample2d_package, and run'python setup.py build ', back ...torch\csrc\api\include\torch/torch.h(7): fatal error C1021: 无效的预处理器命令“warning” error: command 'D:\\vs\\temp\\VC\\Tools\\MSVC\\14.31.31103\\bin\\HostX86\\x64\\cl.exe' failed with exit status 2 How can I deal this
I checked the previous issues that some people have trouble with evaluating code. So I resized the gt image and real image to 256x256 in two ways, bilinear and bicubic....
I didn't read anything in the paper that mentioned training time. For 100,000 iterations, approximately how long to train from scratch?
Hello, I have run your code. Good results have been achieved. But in the fashion dataset(176*256), only SSIM 0.65 was obtained and SSIM_256 is 0.68. Is there any problem with...
It seems that running download.sh has no effect. There is no data that is actually pulled by running wget. Any thoughts?