search

emrahbasaran / SPReID

Code for our CVPR 2018 paper - Human Semantic Parsing for Person Re-identification
MIT License
141 stars 32 forks source link

Much Lower Result & GPU Problem #19

Open wuxifang1994 opened 5 years ago

wuxifang1994 commented 5 years ago

Hi, I use only 1 GPU(GXT 1080Ti 11GB) for training this model. Limited by memory of GPU, I set the batchsize=4 instead of 16 in your code. And I trained the model only on Market-1501 dataset instead of 10 datasets. The result is mAP = 0.385818, r1 precision = 0.627969 much lower than your paper said. So there are two problems.

  1. How many GPUs you used in this experiment? I wonder whether the batchsize mostly influence the accuracy.
  2. If I can't get the whole 10 datasets and only use 1 dataset for training and testing, how much will the result fall? Thank you for your wonderful work. Looking forward to your response.
liiiiiiiiil commented 5 years ago

Hi, I use only 1 GPU(GXT 1080Ti 11GB) for training this model. Limited by memory of GPU, I set the batchsize=4 instead of 16 in your code. And I trained the model only on Market-1501 dataset instead of 10 datasets. The result is mAP = 0.385818, r1 precision = 0.627969 much lower than your paper said. So there are two problems.

  1. How many GPUs you used in this experiment? I wonder whether the batchsize mostly influence the accuracy.
  2. If I can't get the whole 10 datasets and only use 1 dataset for training and testing, how much will the result fall? Thank you for your wonderful work. Looking forward to your response.

Hi, the setting of mine is the same as yours, but the results are so bad--R1=0.355 ,mAP= 0.2111. I think your result is reasonable and could you tell me what evaluation code you use?

yaodonggggggg commented 5 years ago

can you share your main code?,my model's loss alway is about 6.5 whatever the loss when the model saved i use

wuxifang1994 commented 5 years ago

Hi, I use only 1 GPU(GXT 1080Ti 11GB) for training this model. Limited by memory of GPU, I set the batchsize=4 instead of 16 in your code. And I trained the model only on Market-1501 dataset instead of 10 datasets. The result is mAP = 0.385818, r1 precision = 0.627969 much lower than your paper said. So there are two problems.

  1. How many GPUs you used in this experiment? I wonder whether the batchsize mostly influence the accuracy.
  2. If I can't get the whole 10 datasets and only use 1 dataset for training and testing, how much will the result fall? Thank you for your wonderful work. Looking forward to your response.

Hi, the setting of mine is the same as yours, but the results are so bad--R1=0.355 ,mAP= 0.2111. I think your result is reasonable and could you tell me what evaluation code you use?

I use the matlab code offered by market-1501 dataset website. And finally the highest result I got was mAP=0.686, r1=85.6. I have no idea about how to get close to the authors' result.

emrahbasaran commented 5 years ago

Hi,

Hi, I use only 1 GPU(GXT 1080Ti 11GB) for training this model. Limited by memory of GPU, I set the batchsize=4 instead of 16 in your code. And I trained the model only on Market-1501 dataset instead of 10 datasets. The result is mAP = 0.385818, r1 precision = 0.627969 much lower than your paper said. So there are two problems.

  1. How many GPUs you used in this experiment? I wonder whether the batchsize mostly influence the accuracy.

We trained the networks using only one TitanXp GPU. Batch size affects the performance. But I have no idea what performance will be when batch size is 4.

  1. If I can't get the whole 10 datasets and only use 1 dataset for training and testing, how much will the result fall?

In all our experiments, 10 datasets mentioned in the paper were used. Therefore, I don't know how the result will change when a different setting is followed.

Thank you for your wonderful work. Looking forward to your response.

lyt20181102 commented 5 years ago

when i run this code,there are some errors.could someone tell me the environment set,such as the version of python,cupy,chainer,cuda,cudnn and so on .thanks

ajwl-pmli commented 4 years ago

Hello, Do you know how to compute the rank1 and mAP? could you give me the code which compute the rank1 and mAP, My mail is pku1401210454@163.com, Thank you very much! @wuxifang1994 @liiiiiiiiil @yaodonggggggg @lyt20181102 @emrahbasaran

ajwl-pmli commented 4 years ago

Hello, I use the matlab code offered by market-1501 dataset website too, but it report error: Incorrect use of *, internal matrix dimensions must be consistent , Did you make any changes to the evaluation code? Thanks very much for reply!@wuxifang1994