dyh127 / adaptive-exploration-for-unsupervised-person-re-identification Goto Github PK

View Code? Open in Web Editor NEW

30.0 30.0 4.0 570 KB

code of our work : Adaptive Exploration for Unsupervised Person Re-Identification

Python 98.36% Shell 1.64%

adaptive-exploration-for-unsupervised-person-re-identification's People

Contributors

Stargazers

Watchers

Forkers

hehefan gcv9htd chengshuai1992 abandonsea

adaptive-exploration-for-unsupervised-person-re-identification's Issues

test problem

=> Start epoch 60
Test:
Extract Features: [1/27] Time 1.015 (1.015) Data 0.871 (0.871)
Extract Features: [2/27] Time 0.142 (0.579) Data 0.000 (0.436)
Extract Features: [3/27] Time 0.151 (0.436) Data 0.009 (0.293)
Extract Features: [4/27] Time 0.143 (0.363) Data 0.000 (0.220)
Extract Features: [5/27] Time 0.152 (0.321) Data 0.009 (0.178)
Extract Features: [6/27] Time 0.143 (0.291) Data 0.000 (0.148)
Extract Features: [7/27] Time 0.143 (0.270) Data 0.000 (0.127)
Extract Features: [8/27] Time 0.143 (0.254) Data 0.000 (0.111)
Extract Features: [9/27] Time 0.142 (0.242) Data 0.000 (0.099)
Extract Features: [10/27] Time 0.158 (0.233) Data 0.009 (0.090)
Extract Features: [11/27] Time 0.143 (0.225) Data 0.000 (0.082)
Extract Features: [12/27] Time 0.142 (0.218) Data 0.000 (0.075)
Extract Features: [13/27] Time 0.143 (0.212) Data 0.000 (0.069)
Extract Features: [14/27] Time 0.152 (0.208) Data 0.009 (0.065)
Extract Features: [15/27] Time 0.142 (0.204) Data 0.000 (0.061)
Extract Features: [16/27] Time 0.142 (0.200) Data 0.000 (0.057)
Extract Features: [17/27] Time 0.142 (0.196) Data 0.000 (0.053)
Extract Features: [18/27] Time 0.142 (0.193) Data 0.000 (0.050)
Extract Features: [19/27] Time 0.143 (0.191) Data 0.000 (0.048)
Extract Features: [20/27] Time 0.143 (0.188) Data 0.000 (0.045)
Extract Features: [21/27] Time 0.143 (0.186) Data 0.000 (0.043)
Extract Features: [22/27] Time 0.143 (0.184) Data 0.000 (0.041)
Extract Features: [23/27] Time 0.142 (0.182) Data 0.000 (0.039)
Extract Features: [24/27] Time 0.143 (0.181) Data 0.000 (0.038)
Extract Features: [25/27] Time 0.143 (0.179) Data 0.000 (0.036)
Extract Features: [26/27] Time 0.143 (0.178) Data 0.000 (0.035)
Extract Features: [27/27] Time 0.047 (0.173) Data 0.000 (0.034)
Extract Features: [1/125] Time 0.800 (0.800) Data 0.655 (0.655)
Extract Features: [2/125] Time 0.144 (0.472) Data 0.000 (0.328)
Extract Features: [3/125] Time 0.143 (0.362) Data 0.000 (0.219)
Extract Features: [4/125] Time 0.143 (0.307) Data 0.000 (0.164)
Extract Features: [5/125] Time 0.143 (0.274) Data 0.000 (0.131)
Extract Features: [6/125] Time 0.142 (0.252) Data 0.000 (0.109)
Extract Features: [7/125] Time 0.150 (0.238) Data 0.008 (0.095)
Extract Features: [8/125] Time 0.142 (0.226) Data 0.000 (0.083)
Extract Features: [9/125] Time 0.143 (0.217) Data 0.000 (0.074)
Extract Features: [10/125] Time 0.151 (0.210) Data 0.008 (0.067)
Extract Features: [11/125] Time 0.143 (0.204) Data 0.000 (0.061)
Extract Features: [12/125] Time 0.143 (0.199) Data 0.000 (0.056)
Extract Features: [13/125] Time 0.144 (0.195) Data 0.000 (0.052)
Extract Features: [14/125] Time 0.143 (0.191) Data 0.000 (0.048)
Extract Features: [15/125] Time 0.143 (0.188) Data 0.000 (0.045)
Extract Features: [16/125] Time 0.151 (0.185) Data 0.008 (0.043)
Extract Features: [17/125] Time 0.142 (0.183) Data 0.000 (0.040)
Extract Features: [18/125] Time 0.153 (0.181) Data 0.009 (0.038)
Extract Features: [19/125] Time 0.144 (0.179) Data 0.000 (0.036)
Extract Features: [20/125] Time 0.153 (0.178) Data 0.008 (0.035)
Extract Features: [21/125] Time 0.144 (0.176) Data 0.000 (0.033)
Extract Features: [22/125] Time 0.142 (0.175) Data 0.000 (0.032)
Extract Features: [23/125] Time 0.151 (0.174) Data 0.009 (0.031)
Extract Features: [24/125] Time 0.151 (0.173) Data 0.009 (0.030)
Extract Features: [25/125] Time 0.155 (0.172) Data 0.011 (0.029)
Extract Features: [26/125] Time 0.150 (0.171) Data 0.007 (0.028)
Extract Features: [27/125] Time 0.143 (0.170) Data 0.000 (0.027)
Extract Features: [28/125] Time 0.144 (0.169) Data 0.000 (0.026)
Extract Features: [29/125] Time 0.143 (0.168) Data 0.000 (0.025)
Extract Features: [30/125] Time 0.143 (0.168) Data 0.000 (0.025)
Extract Features: [31/125] Time 0.143 (0.167) Data 0.000 (0.024)
Extract Features: [32/125] Time 0.143 (0.166) Data 0.000 (0.023)
Extract Features: [33/125] Time 0.143 (0.165) Data 0.000 (0.022)
Extract Features: [34/125] Time 0.143 (0.165) Data 0.000 (0.022)
Extract Features: [35/125] Time 0.143 (0.164) Data 0.000 (0.021)
Extract Features: [36/125] Time 0.144 (0.163) Data 0.000 (0.021)
Extract Features: [37/125] Time 0.143 (0.163) Data 0.000 (0.020)
Extract Features: [38/125] Time 0.143 (0.162) Data 0.000 (0.019)
Extract Features: [39/125] Time 0.143 (0.162) Data 0.000 (0.019)
Extract Features: [40/125] Time 0.144 (0.161) Data 0.000 (0.018)
Extract Features: [41/125] Time 0.143 (0.161) Data 0.000 (0.018)
Extract Features: [42/125] Time 0.143 (0.161) Data 0.000 (0.018)
Extract Features: [43/125] Time 0.144 (0.160) Data 0.000 (0.017)
Extract Features: [44/125] Time 0.143 (0.160) Data 0.000 (0.017)
Extract Features: [45/125] Time 0.142 (0.159) Data 0.000 (0.016)
Extract Features: [46/125] Time 0.143 (0.159) Data 0.000 (0.016)
Extract Features: [47/125] Time 0.143 (0.159) Data 0.000 (0.016)
Extract Features: [48/125] Time 0.144 (0.158) Data 0.000 (0.015)
Extract Features: [49/125] Time 0.143 (0.158) Data 0.000 (0.015)
Extract Features: [50/125] Time 0.143 (0.158) Data 0.000 (0.015)
Extract Features: [51/125] Time 0.143 (0.157) Data 0.000 (0.015)
Extract Features: [52/125] Time 0.143 (0.157) Data 0.000 (0.014)
Extract Features: [53/125] Time 0.143 (0.157) Data 0.000 (0.014)
Extract Features: [54/125] Time 0.144 (0.157) Data 0.000 (0.014)
Extract Features: [55/125] Time 0.143 (0.156) Data 0.000 (0.013)
Extract Features: [56/125] Time 0.143 (0.156) Data 0.000 (0.013)
Extract Features: [57/125] Time 0.143 (0.156) Data 0.000 (0.013)
Extract Features: [58/125] Time 0.143 (0.156) Data 0.000 (0.013)
Extract Features: [59/125] Time 0.143 (0.156) Data 0.000 (0.013)
Extract Features: [60/125] Time 0.143 (0.155) Data 0.000 (0.012)
Extract Features: [61/125] Time 0.143 (0.155) Data 0.000 (0.012)
Extract Features: [62/125] Time 0.144 (0.155) Data 0.000 (0.012)
Extract Features: [63/125] Time 0.143 (0.155) Data 0.000 (0.012)
Extract Features: [64/125] Time 0.144 (0.155) Data 0.000 (0.012)
Extract Features: [65/125] Time 0.143 (0.154) Data 0.000 (0.011)
Extract Features: [66/125] Time 0.143 (0.154) Data 0.000 (0.011)
Extract Features: [67/125] Time 0.144 (0.154) Data 0.000 (0.011)
Extract Features: [68/125] Time 0.143 (0.154) Data 0.000 (0.011)
Extract Features: [69/125] Time 0.143 (0.154) Data 0.000 (0.011)
Extract Features: [70/125] Time 0.143 (0.154) Data 0.000 (0.011)
Extract Features: [71/125] Time 0.143 (0.153) Data 0.000 (0.010)
Extract Features: [72/125] Time 0.143 (0.153) Data 0.000 (0.010)
Extract Features: [73/125] Time 0.143 (0.153) Data 0.000 (0.010)
Extract Features: [74/125] Time 0.143 (0.153) Data 0.000 (0.010)
Extract Features: [75/125] Time 0.143 (0.153) Data 0.000 (0.010)
Extract Features: [76/125] Time 0.143 (0.153) Data 0.000 (0.010)
Extract Features: [77/125] Time 0.144 (0.153) Data 0.000 (0.010)
Extract Features: [78/125] Time 0.142 (0.153) Data 0.000 (0.010)
Extract Features: [79/125] Time 0.143 (0.152) Data 0.000 (0.009)
Extract Features: [80/125] Time 0.143 (0.152) Data 0.000 (0.009)
Extract Features: [81/125] Time 0.143 (0.152) Data 0.000 (0.009)
Extract Features: [82/125] Time 0.144 (0.152) Data 0.000 (0.009)
Extract Features: [83/125] Time 0.144 (0.152) Data 0.000 (0.009)
Extract Features: [84/125] Time 0.144 (0.152) Data 0.000 (0.009)
Extract Features: [85/125] Time 0.143 (0.152) Data 0.000 (0.009)
Extract Features: [86/125] Time 0.143 (0.152) Data 0.000 (0.009)
Extract Features: [87/125] Time 0.143 (0.152) Data 0.000 (0.009)
Extract Features: [88/125] Time 0.143 (0.151) Data 0.000 (0.008)
Extract Features: [89/125] Time 0.143 (0.151) Data 0.000 (0.008)
Extract Features: [90/125] Time 0.144 (0.151) Data 0.000 (0.008)
Extract Features: [91/125] Time 0.144 (0.151) Data 0.000 (0.008)
Extract Features: [92/125] Time 0.143 (0.151) Data 0.000 (0.008)
Extract Features: [93/125] Time 0.143 (0.151) Data 0.000 (0.008)
Extract Features: [94/125] Time 0.143 (0.151) Data 0.000 (0.008)
Extract Features: [95/125] Time 0.143 (0.151) Data 0.000 (0.008)
Extract Features: [96/125] Time 0.144 (0.151) Data 0.000 (0.008)
Extract Features: [97/125] Time 0.143 (0.151) Data 0.000 (0.008)
Extract Features: [98/125] Time 0.142 (0.151) Data 0.000 (0.008)
Extract Features: [99/125] Time 0.143 (0.151) Data 0.000 (0.008)
Extract Features: [100/125] Time 0.144 (0.150) Data 0.000 (0.007)
Extract Features: [101/125] Time 0.143 (0.150) Data 0.000 (0.007)
Extract Features: [102/125] Time 0.144 (0.150) Data 0.000 (0.007)
Extract Features: [103/125] Time 0.144 (0.150) Data 0.000 (0.007)
Extract Features: [104/125] Time 0.144 (0.150) Data 0.000 (0.007)
Extract Features: [105/125] Time 0.143 (0.150) Data 0.000 (0.007)
Extract Features: [106/125] Time 0.144 (0.150) Data 0.000 (0.007)
Extract Features: [107/125] Time 0.143 (0.150) Data 0.000 (0.007)
Extract Features: [108/125] Time 0.143 (0.150) Data 0.000 (0.007)
Extract Features: [109/125] Time 0.144 (0.150) Data 0.000 (0.007)
Extract Features: [110/125] Time 0.144 (0.150) Data 0.000 (0.007)
Extract Features: [111/125] Time 0.144 (0.150) Data 0.000 (0.007)
Extract Features: [112/125] Time 0.143 (0.150) Data 0.000 (0.007)
Extract Features: [113/125] Time 0.143 (0.150) Data 0.000 (0.007)
Extract Features: [114/125] Time 0.143 (0.150) Data 0.000 (0.007)
Extract Features: [115/125] Time 0.144 (0.150) Data 0.000 (0.007)
Extract Features: [116/125] Time 0.144 (0.150) Data 0.000 (0.006)
Extract Features: [117/125] Time 0.144 (0.149) Data 0.000 (0.006)
Extract Features: [118/125] Time 0.143 (0.149) Data 0.000 (0.006)
Extract Features: [119/125] Time 0.143 (0.149) Data 0.000 (0.006)
Extract Features: [120/125] Time 0.143 (0.149) Data 0.000 (0.006)
Extract Features: [121/125] Time 0.143 (0.149) Data 0.000 (0.006)
Extract Features: [122/125] Time 0.143 (0.149) Data 0.000 (0.006)
Extract Features: [123/125] Time 0.144 (0.149) Data 0.000 (0.006)
Extract Features: [124/125] Time 0.144 (0.149) Data 0.000 (0.006)
Extract Features: [125/125] Time 0.049 (0.148) Data 0.000 (0.006)
./test.sh: line 40: 22718 Segmentation fault (core dumped) python main.py -s ${sourceset} -t ${targetset} --resume ./checkpoint/AE_${sourceset}2${targetset}xi${xi}/checkpoint.pth.tar --data-dir /home/yy1048229281/data/ --evaluate

I completed the training without problems, I completed the training without problems, but I encountered this problem when I started testing, I changed my torch version, but it still can't be solved, do you have any suggestions?
This is my current version
torch 1.0.1
torchvision 0.2.2

What is the precise version of pytorch and cuda

I have tried pytorch(1.0.0) and cuda(8.0).
But I received the error:

log_dir= checkpoint/AE_duke2market_xi_0.6
Namespace(arch='resnet50', batch_size=128, data_dir='data/', delta=3.5, dropout=0.5, epochs=60, epochs_decay=40, evaluate=False, features=4096, height=256, lambda0=0.55, logs_dir='checkpoint/AE_duke2market_xi_0.6', lr=0.1, momentum=0.9, mu=0.4, output_feature='pool5', print_freq=50, re=0.5, resume='', source='duke', target='market', tau=0.05, weight_decay=0.0005, width=128, workers=8, xi=0.6)
For target train set, indexes are treated as identities of images
Data dataset loaded
  subset   | # ids | # images
  ---------------------------
  source train    |     0 |        0
  target train    |     0 |        0
  query    |     0 |        0
  gallery  |     0 |        0
Traceback (most recent call last):
  File "main.py", line 231, in <module>
    main(args)
  File "main.py", line 101, in main
    args.re, args.workers)
  File "main.py", line 52, in get_data
    shuffle=True, pin_memory=True, drop_last=True)
  File "/home/yl/anaconda3/envs/python3.6/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 802, in __init__
    sampler = RandomSampler(dataset)
  File "/home/yl/anaconda3/envs/python3.6/lib/python3.6/site-packages/torch/utils/data/sampler.py", line 64, in __init__
    "value, but got num_samples={}".format(self.num_samples))
ValueError: num_samples should be a positive integeral value, but got num_samples=0

I think it is caused by incorrect version of pytorch and cuda

Can you share the trained model on market only and duke only？

The training takes longer，can you share the trained model on market only and duke only？

Adaptive-Exploration-for-Unsupervised-Person-Re-Identification/reid/nonparametric_classifier.py, as for line 54 loss = F.cross_entropy(inputs, targets), 'targets' seems like target domain real labels?

Hi, there in the Adaptive-Exploration-for-Unsupervised-Person-Re-Identification/reid/nonparametric_classifier.py, as for line 54:

loss = F.cross_entropy(inputs, targets), 'targets' seems like target domain real labels?

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.