Very nice work！I can't find the D3DFR_222.txt in the raw BFM models files.
Could you please provide 222 landmarks txt? I want to test the performance in more keypoints ?
https://github.com/FaceAdapter/Face-Adapter/blob/main/third_party/d3dfr/bfm.py#L88
# keypoints_222 = [] # with open(os.path.join(CURRENT_PATH, 'BFM/D3DFR_222.txt'), 'r') as f: # for line in f.readlines(): # idx = int(line.strip()) # keypoints_222.append(max(idx, 0)) # self.register_buffer('keypoints_222', torch.from_numpy(np.array(keypoints_222)).long())
Looking forward to your reply
Very nice work！I can't find the D3DFR_222.txt in the raw BFM models files.
Could you please provide 222 landmarks txt? I want to test the performance in more keypoints ?
https://github.com/FaceAdapter/Face-Adapter/blob/main/third_party/d3dfr/bfm.py#L88
# keypoints_222 = [] # with open(os.path.join(CURRENT_PATH, 'BFM/D3DFR_222.txt'), 'r') as f: # for line in f.readlines(): # idx = int(line.strip()) # keypoints_222.append(max(idx, 0)) # self.register_buffer('keypoints_222', torch.from_numpy(np.array(keypoints_222)).long())Looking forward to your reply