DragGAN
DragGAN copied to clipboard
Unofficial Implementation of DragGAN - "Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold" (DragGAN 全功能实现,在线Demo,本地部署试用,代码、模型已全部开源,支持Wi...
RuntimeError: The size of tensor a (1024) must match the size of tensor b (300) at non-singleton dimension 3
Traceback (most recent call last): File "D:\python\ws\venv\lib\site-packages\gradio\routes.py", line 408, in run_predict output = await app.get_blocks().process_api( File "D:\python\ws\venv\lib\site-packages\gradio\blocks.py", line 1313, in process_api inputs = self.preprocess_data(fn_index, inputs, state) File "D:\python\ws\venv\lib\site-packages\gradio\blocks.py", line 1163,...
Uploading a new image will result in a collapsed image. What should I do? Upload the first image and you will see the second image.  
想请问一下,这个版本和原作者的版本有什么关系

您好, 使用上述代码会在load_state_dict时报错 请问是在加载customgenrator时哪里参数设置的不对吗? 还是在训练时有某些参数是需要写死的呢? 训练使用的是pytorch-ada-pytorch,参数使用的是默认参数,训练了92220张256x256的图片,命令如下 python train.py --outdir=~/training-runs --data=~/mydataset.zip --gpus=1 参数如下 { "num_gpus": 1, "image_snapshot_ticks": 50, "network_snapshot_ticks": 50, "metrics": [ "fid50k_full" ], "random_seed": 0, "training_set_kwargs": { "class_name": "training.dataset.ImageFolderDataset", "path": "./anime.zip",...
build-in images works: before: after: but upload my own image has bad quality to even start: original image:  after uploading: any pointers? thanks!
The user wants to download the checkpoint to the project directory instead of the system drive.
I can not load the web page, because gradio can not work fine when no internet connection. any one can help?
