facexlib
facexlib copied to clipboard
xinntao
FaceXlib aims at providing ready-to-use face-related functions based on current STOA open-source methods.
Some code in the system will apply for resources on cuda:0, although I have specified other gpuid. This commit solves the problem
Thank you for perfect work. But like this: "device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')", Sometimes, I will use 'cuda:1'. Please fix it.
Now！ Function get_face_landmarks_5 Detect_faces Second individual number 0.97, Nyoka demand repair source code, Incapable individual number direct change This individual, Unnecessary repair utils / face_resoration_helper.py Please!
Hi, i'd like to know is the model retinaface trained on RGB or BGR? if i applied direct on RGB, will the precision changes a lot? Thanks for reply!
I am using this image in https://github.com/TencentARC/GFPGAN and the background turns black after calling `paste_faces_to_input_image`. Is there a way to implement support for PNG transparent background?  Thanks
Could not import ResNetArcFace, cosin_metric, load_image in inference/inference_recognition.py
Hello, in face_restoration_helper.py i see that you are using different models: face detection, landmark detection and a segmentation model. This causes cuda out of memory errors in even GPUs with...
Can you change this line only so we can use CPU or GPU. FROM: model = Backbone(num_layers=50, drop_ratio=0.6, mode='ir_se').to(**'cuda'**).eval() TO: model = Backbone(num_layers=50, drop_ratio=0.6, mode='ir_se').to(**device**).eval()
Hello, detection_Resnet50_Final.pth and parsing_parsenet.pth make my nvidia pc slow..just wanna ask if they got onnx version
# Problem: At the main [README](https://github.com/xinntao/facexlib/blob/master/README.md#sparkles-functions), there is a table with a few internal links: | Link Status | Link | :--- | :--- | | ⚠️ Non-existing link |...
