I got worse performance in triplet_loss.py about open-reid HOT 7 CLOSED

Please provide as much information as possible.
For example:

• your platform?
• your pytorch version?
• open-reid version?

from open-reid.

@zydou sorry! I ran it in Ubuntu system with python 2.7.6, pytorch version 0.2.0_3 and open-reid version 0.2.0.

from open-reid.

Try to use python3.

from open-reid.

Hi @zydou
I changed my python version from 2.7 to 3.5
But I still cannot achieve the best results in the benchmark table
The triplet loss on the market-1501 has 67.9 mAP, but I got the 60.5 mAP.
Here is my results on the test set

Mean AP: 60.5%
CMC Scores    allshots      cuhk03  market1501
  top-1          33.2%       62.9%       78.2%
  top-5          50.4%       88.0%       91.2%
  top-10         59.1%       93.3%       94.4%

I trained the model for market-1501 dataset using the following parameters:

batchsize=64
lr=0.00005
epochs=600

I have one GPU, so I modified the batchsize from 256 to 64, changed the learning rate from 0.0002 to 0.00005 and changed the epochs from 150 to 600 according to tips-and-tricks
I used the triplet loss and resnet-50 network.
What's wrong with my training?
Would you please help me?

from open-reid.

Larger batch size is better for hard mining, and gives better performance.
Please refer to #28 and #43 for more information.

from open-reid.

Thank you for your help.

from open-reid.

@zydou thanks a lot for your detailed explanations!

from open-reid.