CodeFormer
CodeFormer copied to clipboard
sczhou
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
Traceback (most recent call last): File "/data/workpace/CodeFormer/inference_codeformer.py", line 190, in num_det_faces = face_helper.get_face_landmarks_5( File "/data/workpace/CodeFormer/facelib/utils/face_restoration_helper.py", line 217, in get_face_landmarks_5 bboxes = self.face_detector.detect_faces(input_img) File "/data/workpace/CodeFormer/facelib/detection/retinaface/retinaface.py", line 205, in detect_faces image, self.resize...
I have been trying to upscale some photos of Asian people using CodeFormer, but when the converted images come out, the eyes and features of the individuals seem to have...
Please give me some examples. I can run images perfectly with the examples. However, other than that, none of them work. Is it problem that most of training are european...
i cant do anything cause of it
>python basicsr/setup.py develop Traceback (most recent call last): File "F:\CodeFormer\basicsr\setup.py", line 10, in from utils.misc import gpu_is_available File "F:\CodeFormer\basicsr\utils\__init__.py", line 2, in from .img_util import crop_border, imfrombytes, img2tensor, imwrite, tensor2img...
I have tried everything to solve this error, but couldn't do it. I am running of colab. Has anyone else faced any kind of issue similar to this, or can...
![Uploading 000000_00.png…]()
