Get R1=90.00% and mAP=82.79%. about ste-nvan HOT 4 CLOSED

Hi
You can follow the Usage-testing part in Readme.

from ste-nvan.

I have run the code:
1.train:
CKPT=ckpt_NL_0230
python3 train_NL.py --train_txt $TRAIN_TXT --train_info $TRAIN_INFO --batch_size 64
--n_epochs 200 --lr 0.001 --lr_step_size 50 --optimizer adam --ckpt $CKPT --log_path loss.txt --class_per_batch 8
--model_type 'resnet50_NL' --num_workers 8 --track_per_class 4 --S 8 --latent_dim 2048 --temporal Done --track_id_loss
--non_layers 0 2 3 0
2.evaluate:
LOAD_CKPT=.ckpt_NL_0230/ckpt_best.pth
python3 evaluate.py --test_txt $TEST_TXT --test_info $TEST_INFO --query_info $QUERY_INFO
--batch_size 64 --model_type 'resnet50_NL' --num_workers 8 --S 8 --latent_dim 2048
--temporal Done --non_layers 0 2 3 0 --load_ckpt $LOAD_CKPT \

the result is very bad,CMC : 0.6374 , mAP : 0.4554,Is there anything wrong?

from ste-nvan.

I have run the code:
1.train:
CKPT=ckpt_NL_0230
python3 train_NL.py --train_txt $TRAIN_TXT --train_info $TRAIN_INFO --batch_size 64
--n_epochs 200 --lr 0.001 --lr_step_size 50 --optimizer adam --ckpt $CKPT --log_path loss.txt --class_per_batch 8
--model_type 'resnet50_NL' --num_workers 8 --track_per_class 4 --S 8 --latent_dim 2048 --temporal Done --track_id_loss
--non_layers 0 2 3 0
2.evaluate:
LOAD_CKPT=.ckpt_NL_0230/ckpt_best.pth
python3 evaluate.py --test_txt $TEST_TXT --test_info $TEST_INFO --query_info $QUERY_INFO
--batch_size 64 --model_type 'resnet50_NL' --num_workers 8 --S 8 --latent_dim 2048
--temporal Done --non_layers 0 2 3 0 --load_ckpt $LOAD_CKPT \

the result is very bad,CMC : 0.6374 , mAP : 0.4554,Is there anything wrong?

Same as mine. Have you figure out where the problem is ?

from ste-nvan.

Hi @hanzhs and @huo123lijuan
I found that I type the wrong learning rate in the script file.
I should be 1e-4 (0.0001)!

Thanks!

from ste-nvan.