Comments (4)
I have the same question, the performance decreases to 77.8% (mAP) and 89.9% (top-1) when choosing the "use-hard" option.
Could you tell me why CM_hard does not show any advantages compared to CM?
from cluster-contrast-reid.
Sorry that we didn't not provides the CM_hard command in readme.md. I will update it.
For this command:
CUDA_VISIBLE_DEVICES=0,1,2,3 python examples/cluster_contrast_train_usl.py -b 256 -a resnet_ibn50a -d market1501 --iters 400 --momentum 0.1 --eps 0.4 --num-instances 16 --pooling-type gem --use-hard --logs-dir /data0/developer/cluster-contrast/examples/logs/gem-hard
You will get result:
Mean AP: 87.0%
CMC Scores:
top-1 94.6%
top-5 98.2%
top-10 98.8%
which is much higher than paper result since we use gem pooling.
If use average pooling like:
CUDA_VISIBLE_DEVICES=0,1,2,3 python examples/cluster_contrast_train_usl.py -b 256 -a resnet_ibn50a -d market1501 --iters 400 --momentum 0.1 --eps 0.4 --num-instances 16 --pooling-type avg --use-hard
You will get result similar or a litter higher than our paper:
Mean AP: 84.5%
CMC Scores:
top-1 93.6%
top-5 97.5%
top-10 98.4%
Thank!
from cluster-contrast-reid.
Using CM_hard will get better result, but it requires carefully selected hyper-parameters. Generally, we recommend using CM first, and then try CM_hard for different hyper-parameters.
from cluster-contrast-reid.
from my test,I choose batchsize 128 model resnet dataset market1501 --iters 400 --momentum 0.1 --eps 0.4 --num-instances 16 --pooling-type gem . when I choose use-hard ,mAP is 78.0. but when I use common CM ,mAP is 80.8
from cluster-contrast-reid.
Related Issues (20)
- Sorry that we didn't not provides the CM_hard command in readme.md. I will update it. HOT 2
- i see in the experiment you only train in batch 256,different from that in method like spcl,and is the good result get by larger batchsize? HOT 7
- How to determine the EPS parameters of DBSCAN for different datasets? HOT 1
- Can't reproduce MSMT17 results HOT 8
- 关于Memory Initialization的一点问题 HOT 4
- Why is the performance of the model trained with multi GPUs much better than that of the model trained with single GPU in this method? HOT 5
- 关于use hard的问题 HOT 4
- I downloaded the trained model you released, but only market and Dukle. Can you publish the model trained on VeRi? HOT 1
- PersonX 数据集上mAP只有36.0左右 HOT 6
- why don't use pseudo_labeled=-1 ?
- Why hard sampling is only beneficial for resnet_ibn_a?
- Why the result cannot be reproduced? HOT 2
- Different methods in memory update
- About the setting of batch_size and iter number HOT 1
- 为啥msmt17的指标sota都只有20多呢? HOT 1
- Warning: Leaking Caffe2 thread-pool after fork.
- Can't reproduce the result of MTMC17 to 33.3 using avg pooling HOT 2
- dataset HOT 4
- Why this paper is not accepted... HOT 1
- 运行问题 HOT 1
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 cluster-contrast-reid.