ValueError: zero-dimensional arrays cannot be concatenated

[chj1933]

when I run sh demo.sh
[INFO] Making loss...
1.000 * CrossEntropy
1.000 * Triplet
[INFO] Epoch: 1 Learning rate: 2.00e-04

[INFO] Test:
Traceback (most recent call last):
File "main.py", line 22, in
trainer.test()
File "/media/data2/chenghj/RE-ID/MGN-pytorch-master/trainer.py", line 74, in test
dist = re_ranking(q_g_dist, q_q_dist, g_g_dist)
File "/media/data2/chenghj/RE-ID/MGN-pytorch-master/utils/re_ranking.py", line 44, in re_ranking
[np.concatenate([q_q_dist, q_g_dist], axis=1),
ValueError: zero-dimensional arrays cannot be concatenated

please tell me how to correct it . thanks!

[seathiefwang]

can you show me your demo.sh file? it is ok when i run it.

[chj1933]

@seathiefwang ，if I want to use my own dataset , how to train it?

[seathiefwang]

You need to write code to parse your data.

[chj1933]

@seathiefwang , If i use my own dataset , It's appropriate what parameters should I usually adjust?

[seathiefwang]

--datadir you need modify this parameter.

[chj1933]

@seathiefwang ，thanks! It works when I use my own dataset , but the mAP and rank1 are not very high , if I want to improve the mAP and rank1, It's appropriate what parameters should I usually adjust?

[seathiefwang]

#1

[chj1933]

@seathiefwang ，please tell me how are your training parameters set？I always lower 1% than your, it can't achieve rank1 95.8% and mAP 93.5%

[chj1933]

@seathiefwang , why is lower when I use 4 GPUS than 2 GPUS, other parameters remain the same

[seathiefwang]

You can change parameters and try more times.

[chj1933]

@seathiefwang ，你好，若果我用自己的数据训练，我在解析自己的数据时候除了修改（market1501.py）把ID信息和摄像头信息导入,还要修改哪里嘛？不然会在dist = cdist(qf,gf)显示XA must be a 2-dimensional array