embed

[qujinjie]

for it, (img, lb_id) in enumerate(dl):
    print('\r=======>  processing iter {} / {}'.format(it, all_iter_nums),
            end = '', flush = True)
    label_ids.append(lb_id)
    #label_cams.append(lb_cam)
    embds = []
    for im in img:
        im = im.cuda()
        embd = model(im).detach().cpu().numpy() #通过网络生成特征向量
        embds.append(embd)
    embed = sum(embds) / len(embds)
    embeddings.append(embed)

请问代码为什么每次要把一个ｂａｔｃｈ的特征求和除去长度

[bitgs]

I think there is a problem too.

[bitgs]

I guess the author wanted to sum up the embeddings of ten crops of 1 image rather than a batch of 32 images.