UMEI

Results 8 comments of UMEI

非常感谢同学帮我解答,但是我还是不明白,code中对tripletfolder.py中anchor、pos、neg进行了定义: def _get_pos_sample(self, target, index): pos_index = np.argwhere(self.targets == target) # 正样本 与anchor同身份但是不相似的行人 pos_index = pos_index.flatten() pos_index = np.setdiff1d(pos_index, index) rand = np.random.permutation(len(pos_index)) result_path = [] for i in range(4):...

正负样本不应该分别对应anchor同身份和不同身份的行人嘛?计算loss时,这个code内正负样本选择的都是同身份中的行人呐? neg_labels = pos_labels # hard-neg # ---------------------------------- nf_data = pf # 负样本的特征直接取自于正样本的特征呐?后面计算的就都是正样本中,与anchor距离最远的正样本了? # 128 is too much, we use pool size = 64 rand = np.random.permutation(4*opt.batchsize)[0:opt.poolsize] nf_data = nf_data[rand,:]...

有个问题请教一下,pf_hard和nf_hard都是从从相同身份的行人中选取出来的,都是正样本,为什么code里是nes_label=pos_lable呢?详见Ony have anchor and pos_sample #26

hi, can you help me about this question? [https://github.com/qiaoguan/Person-reid-GAN-pytorch/issues/26](url) Thank you very much!

> You can execute this file. > This creates the train_new folder. > > `python re_index.py ` > > ## ---------------------re_index.py------------------------ > import os > from shutil import copyfile >...

整体代码我都看过了,很感谢的分享。让我不懂的就是这个提示错误的地方,else后面应该指的是读取非gen_0000的文件名索引,但是报错却是提醒我说gen_0000中的图片索引读不进去,让我很费解。

Wow, Thanks for your answer! I got it!