PaddleGAN icon indicating copy to clipboard operation
PaddleGAN copied to clipboard

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.

Results 261 PaddleGAN issues
Sort by recently updated
recently updated
newest added

This PR redesigns the logging system in GAN without changing any of the console logging. The proposed change is to have a BaseLogger class from which new loggers can inherit....

contributor

``` Traceback (most recent call last): File "tools/main.py", line 56, in main(args, cfg) File "tools/main.py", line 32, in main trainer = Trainer(cfg) File "/home/lizhaohui/PaddleGAN/ppgan/engine/trainer.py", line 134, in __init__ self.lr_schedulers =...

如果自己训练wav2lip,数据格式是什么样的呢?可以提供一个例子吗?

(zh version after en | 英文后面是中文) ## Why? | 为什么? Locking librosa strictly to v0.8.1 makes PaddleGAN more difficult to be used with other packages. --- 把 librosa 版本严格锁在 v0.8.1...

- Found Paddle host system: ubuntu, version: 20.04.4 -- Found Paddle host system's CPU: 40 cores -- CMAKE_CXX_FLAGS: -flto -- CMAKE_CXX_FLAGS_RELEASE: CMake Error at cmake/os/android.cmake:23 (message): Must set ANDROID_NDK or...

我看到代码有gpen的restoration实现,请问你们试过SR么?比如4x的效果,谢谢

基础环境: TensorFlow 2.8.0 + PyTorch 1.11.0 + conda/mamba + opencv 4 + CUDA11.6/cudnn8.4.0 + Python3.9.12 过程: 尝试PIP安装paddlepaddle后测试安装成功; 尝试Conda方式安装paddlepaddle后测试安装成功; 问题: 执行python -u applications/tools/first-order-demo.py --driving_video 34.mp4 --source_image 1.jpg --relative --adapt_scale --face_enhancement --output...