Closed Niculuse closed 6 years ago
Please provide as much information as possible. For example:
@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.
Try to use python3.
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?
Larger batch size is better for hard mining, and gives better performance. Please refer to #28 and #43 for more information.
Thank you for your help.
@zydou thanks a lot for your detailed explanations!
I ran the triplet_loss.py on market1501 as told in benchmark, but I got worse result that every item is about 5% lower than presented in bemchmark. BTW, I didn't change code. I do not understand why.Can you help me? Thanks!