RankPose
RankPose copied to clipboard
RankPose: Learning Generalised Feature with Rank Supervision for Head Pose Estimation
Validation is done in 1969 images of AFLW2000 (not 2000 in paper).
Hello, in your paper you use l1 ranking loss, but your code is l2 ranking loss, can you explain that. BTW, I have tried both and l2 outperforms l1 little.
Where is test.py?
I The loss function of nn.MarginRankingLoss is "loss(x1,x2,y)=max(0,−y∗(x1−x2)+margin) " where y expect 1 or -1, but labels only has value in 0 or 1
In RankPose/src/dataset/biwi.py with open(filename, 'r') as f: # data/biwi_dataset_list.txt for i, line in enumerate(f.readlines()): ls = line.strip().split(' ') bbox = [float(ls[i]) for i in range(1,5)] pose = [float(ls[i]) for i...
In RankPose/src/dataset/biwi.py with open(filename, 'r') as f: # data/biwi_dataset_list.txt for i, line in enumerate(f.readlines()): ls = line.strip().split(' ') bbox = [float(ls[i]) for i in range(1,5)] pose = [float(ls[i]) for i...