Easy training on custom dataset. Various backends (MobileNet and SqueezeNet) supported. A YOLO demo to detect raccoon run entirely in brower is accessible at https://git.io/vF7vI (not on Windows).
conf_mask why not use y_true mask:
if y_true[i,4]=1 , it means there have a box, and conf_mask[i]=1,
why still need to compute the IOU between y_pred with y_true box , and then judge the conf_mask through :conf_mask= conf_mask + tf.to_float(best_ious < 0.6) * (1 - y_true[..., 4])
conf_mask why not use y_true mask: if y_true[i,4]=1 , it means there have a box, and conf_mask[i]=1,
why still need to compute the IOU between y_pred with y_true box , and then judge the conf_mask through :
conf_mask= conf_mask + tf.to_float(best_ious < 0.6) * (1 - y_true[..., 4])