Comments (3)
Hi, thanks for your attention. Make sure that Python and Pytorch versions are the same as in README.
from person-reid-triplet-loss-baseline.
Hi, thanks for your response, I am running on exact environment python 2.7 and torch 0.3 but I can't reproduce the results of pretrained model. I again downloaded the weights also checked for my sci-kit learn version. Following is the log that I am encountering. Any pointers from you will be really appreciated.
(ccis) iacvlab@iacvlab-desktop:~/anurag/ccis/dynamic-re-ranking$ ./run.sh
------------------------------------------------------------
cfg.__dict__
{'base_lr': 0.0002,
'ckpt_file': '/home/iacvlab/anurag/ccis/results/ckpt.pth',
'crop_prob': 0,
'crop_ratio': 1,
'dataset': 'market1501',
'epochs_per_val': 10000000000.0,
'exp_decay_at_epoch': 151,
'exp_dir': '/home/iacvlab/anurag/ccis/results/',
'ids_per_batch': 32,
'im_mean': [0.486, 0.459, 0.408],
'im_std': [0.229, 0.224, 0.225],
'ims_per_id': 4,
'last_conv_stride': 1,
'log_to_file': True,
'lr_decay_type': 'exp',
'margin': 0.3,
'model_weight_file': '/home/iacvlab/anurag/ccis/weights/market1501_stride1/model_weight.pth',
'normalize_feature': False,
'only_test': True,
'prefetch_threads': 2,
'resize_h_w': (256, 128),
'resume': False,
'run': 1,
'scale_im': True,
'seed': None,
'staircase_decay_at_epochs': (101, 201),
'staircase_decay_multiply_factor': 0.1,
'stderr_file': '/home/iacvlab/anurag/ccis/results/stderr_2019-11-18_14:47:07.txt',
'stdout_file': '/home/iacvlab/anurag/ccis/results/stdout_2019-11-18_14:47:07.txt',
'steps_per_log': 20,
'sys_device_ids': (0,),
'test_batch_size': 32,
'test_final_batch': True,
'test_mirror_type': None,
'test_set_kwargs': {'batch_dims': 'NCHW',
'batch_size': 32,
'final_batch': True,
'im_mean': [0.486, 0.459, 0.408],
'im_std': [0.229, 0.224, 0.225],
'mirror_type': None,
'name': 'market1501',
'num_prefetch_threads': 2,
'part': 'test',
'prng': <module 'numpy.random' from '/home/iacvlab/anaconda3/envs/ccis/lib/python2.7/site-packages/numpy/random/__init__.pyc'>,
'resize_h_w': (256, 128),
'scale': True,
'shuffle': False},
'test_shuffle': False,
'total_epochs': 300,
'train_final_batch': False,
'train_mirror_type': 'random',
'train_set_kwargs': {'batch_dims': 'NCHW',
'crop_prob': 0,
'crop_ratio': 1,
'final_batch': False,
'ids_per_batch': 32,
'im_mean': [0.486, 0.459, 0.408],
'im_std': [0.229, 0.224, 0.225],
'ims_per_id': 4,
'mirror_type': 'random',
'name': 'market1501',
'num_prefetch_threads': 2,
'part': 'trainval',
'prng': <module 'numpy.random' from '/home/iacvlab/anaconda3/envs/ccis/lib/python2.7/site-packages/numpy/random/__init__.pyc'>,
'resize_h_w': (256, 128),
'scale': True,
'shuffle': True},
'train_shuffle': True,
'trainset_part': 'trainval',
'val_set_kwargs': {'batch_dims': 'NCHW',
'batch_size': 32,
'final_batch': True,
'im_mean': [0.486, 0.459, 0.408],
'im_std': [0.229, 0.224, 0.225],
'mirror_type': None,
'name': 'market1501',
'num_prefetch_threads': 2,
'part': 'val',
'prng': <module 'numpy.random' from '/home/iacvlab/anaconda3/envs/ccis/lib/python2.7/site-packages/numpy/random/__init__.pyc'>,
'resize_h_w': (256, 128),
'scale': True,
'shuffle': False},
'weight_decay': 0.0005}
------------------------------------------------------------
----------------------------------------
market1501 test set
----------------------------------------
NO. Images: 31969
NO. IDs: 751
NO. Query Images: 3368
NO. Gallery Images: 15913
NO. Multi-query Images: 12688
----------------------------------------
Loaded model weights from /home/iacvlab/anurag/ccis/weights/market1501_stride1/model_weight.pth
=========> Test on dataset: market1501 <=========
Extracting feature...
1000/1000 batches done, +1.84s, total 95.58s
Done, 95.69s
Computing distance...
Done, 2.10s
Computing scores...
Done, 12.09s
Single Query: [mAP: 2.08%], [cmc1: 8.11%], [cmc5: 17.10%], [cmc10: 23.16%]
Multi Query, Computing distance...
Done, 2.09s
Multi Query, Computing scores...
Done, 12.09s
Multi Query: [mAP: 2.93%], [cmc1: 11.82%], [cmc5: 24.76%], [cmc10: 31.21%]
Re-ranking based on proposed algo...
from person-reid-triplet-loss-baseline.
Thanks for your time. I was initially running code in python3 environment. After changing the environment back to exactly like described in readme code started behaving absurdly. (poor results)
I cloned repo again and it fixed it.
from person-reid-triplet-loss-baseline.
Related Issues (20)
- How can I refer your model in my paper HOT 1
- the different with open-reid HOT 1
- 关于一个epoch中的step数目 HOT 2
- Performance is worse than yours
- 关于d_ap的值 HOT 5
- Error: when i try to run train.py (no module named tri_loss. dataset ) HOT 1
- except Exception, msg: SyntaxError: invalid syntax
- 为什么triloss用的是MarginRankingLoss而不是TripletMarginLoss
- dist_mat[is_pos].contiguous().view(N, -1), 1, keepdim=True) seems wrong HOT 1
- dist_mat[is_pos].contiguous().view(N, -1), 1, keepdim=True) HOT 2
- 关于实现和paper的区别,请指点一下 HOT 5
- 你好,您的cuda和cudnn选的是什么版本呢 HOT 1
- 关于实验性能请教 HOT 1
- Rank 1, 5, 10 are high, but mAP is low HOT 1
- 损失函数是不是可以更直接呢 HOT 2
- how to save my im_paths and features? HOT 1
- Hi how to train your code with different pre-trained models HOT 4
- 热图
- hard triplet convergence
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 person-reid-triplet-loss-baseline.