Open yiyang186 opened 3 years ago
https://github.com/qqwweee/keras-yolo3/blob/e6598d13c703029b2686bc2eb8d5c09badf42992/yolo3/model.py#L398
# K.binary_crossentropy is helpful to avoid exp overflow. xy_loss = object_mask * box_loss_scale * K.binary_crossentropy(raw_true_xy, raw_pred[...,0:2], from_logits=True) wh_loss = object_mask * box_loss_scale * 0.5 * K.square(raw_true_wh-raw_pred[...,2:4])
You add square loss for wh, I think that is a good job really. But I don't understand why it also need to add binary_crossentropy loss for xy. xy = sigmoid(raw_xy) I think xy con not overflow.
https://github.com/qqwweee/keras-yolo3/blob/e6598d13c703029b2686bc2eb8d5c09badf42992/yolo3/model.py#L398
You add square loss for wh, I think that is a good job really. But I don't understand why it also need to add binary_crossentropy loss for xy. xy = sigmoid(raw_xy) I think xy con not overflow.