Open yangglebin opened 5 years ago
in your code(data_detector.py class LabelMapping ) : if self.phase == 'train' and self.num_neg > 0: neg_z, neg_h, neg_w, neg_a = np.where(label[:, :, :, :, 0] == -1) neg_idcs = random.sample(range(len(neg_z)), min(num_neg, len(neg_z))) neg_z, neg_h, neg_w, neg_a = neg_z[neg_idcs], neg_h[neg_idcs], neg_w[neg_idcs], neg_a[neg_idcs] label[:, :, :, :, 0] = 0 label[neg_z, neg_h, neg_w, neg_a, 0] = -1
I noticed that you let num_neg=800 in final label, and set these locations equals to -1, what is this mean? Does it denote number of negative samples you choose? in label, 0 is object(foreground)? 1 is for? -1 is for?
in your code(data_detector.py class LabelMapping ) : if self.phase == 'train' and self.num_neg > 0: neg_z, neg_h, neg_w, neg_a = np.where(label[:, :, :, :, 0] == -1) neg_idcs = random.sample(range(len(neg_z)), min(num_neg, len(neg_z))) neg_z, neg_h, neg_w, neg_a = neg_z[neg_idcs], neg_h[neg_idcs], neg_w[neg_idcs], neg_a[neg_idcs] label[:, :, :, :, 0] = 0 label[neg_z, neg_h, neg_w, neg_a, 0] = -1
I noticed that you let num_neg=800 in final label, and set these locations equals to -1, what is this mean? Does it denote number of negative samples you choose? in label, 0 is object(foreground)? 1 is for? -1 is for?