Closed delaprada closed 1 year ago
The evaluation code is adapted from https://github.com/microsoft/human-pose-estimation.pytorch/blob/18f1d0fa5b5db7fe08de640610f3fdbdbed8fb2f/lib/core/evaluate.py
.
The accuracy function strictly set the threshold to 0.5, yet it corresponds to a fraction α = 0.05 of the image size. See code https://github.com/thuml/Transfer-Learning-Library/blob/b731e85e8e9eb79315da54a6fbe3c3efbf810adf/tllib/utils/metric/keypoint_detection.py#L79
norm = np.ones((pred.shape[0], 2)) * np.array([h, w]) / 10
Thank you for your kindly explanation! I understand what you mean. @JunguangJiang
Hello!
I read the paper of "Regressive Domain Adaptation for Unsupervised Keypoint Detection" today and found that the PCK threshold setting is described in the paper as below:
But when I read the source code: https://github.com/thuml/Transfer-Learning-Library/blob/b731e85e8e9eb79315da54a6fbe3c3efbf810adf/examples/domain_adaptation/keypoint_detection/erm.py#L247 I found that the accuracy function strictly set the threshold to 0.5.
So which one should I choose when I do my experiment would be better? A fraction α = 0.05 of the image size or 0.5?
Thank you.