Comments (4)
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.
Related Issues (20)
- Anybody get the paper's result? Rank1 90%. HOT 5
- Some questions in reproducing the result of NVAN network HOT 5
- Counfusion with position of non-local block HOT 2
- DukeMTMC-videoreid dataset HOT 1
- how to get more rank results? HOT 1
- training on Two GPUs, get the results cmc=87.5, map=33.1. ??? HOT 2
- runtimeerror:Expected object of scalar type Bool but got scalar type Byte for argument #2 'other' in call to _th_xor HOT 2
- Cannot reproduce the ideal accuracy of NVAN HOT 1
- counting FLOPs HOT 2
- Duke training script HOT 1
- Why choose non_layers=[0, 2, 3, 0] and stripes=[16, 16, 16, 16] as your baseline implementation? HOT 3
- DukeMTMC-videoReID dataset preprocess HOT 1
- the problem is here HOT 3
- pretrained model? HOT 1
- Evaluate on Duke-Video datasets HOT 2
- another problem is here. HOT 1
- 随机种子问题 HOT 1
- About Trip loss
- About trained model.
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ste-nvan.