liuzhongling

icon indicating a website link http://liuzhongling.github.io/ icon indicating an email [email protected]

icon company FUJITSU icon location Beijing icon location You cannot improve your past, but you can improve your future. Once time is wasted, life is wasted.

Results 1 issues of liuzhongling

Why use " labels.append(np.ones(dists.size(0)))" in training? and

3 comment

dists = l2_dist.forward(embed_anchor, embed_pos) distances.append(dists.data.cpu().numpy()) labels.append(np.ones(dists.size(0))) dists = l2_dist.forward(embed_anchor, embed_neg) distances.append(dists.data.cpu().numpy()) labels.append(np.zeros(dists.size(0))) can you exlpain the code ? what's for?