Comments (5)
you don't need cluster_list on line 366,it takes up 6GB,beacuse cluster.components_ is a is a matrix shape of (15xxx,16552),you can see this in site-packages/sklearn/cluster/dbscan_.py.
I think eps_list can have the same effect.
I don't know if I am right, please tell me
hello,Have you verified your conjecture?
from self-similarity-grouping.
from self-similarity-grouping.
yes,I try my code and get the same result,and it's evident right
…
------------------ 原始邮件 ------------------ 发件人: "One J"<[email protected]>; 发送时间: 2020年3月28日(星期六) 晚上10:39 收件人: "OasisYang/SSG"<[email protected]>; 抄送: "朱方琪"<[email protected]>; "Author"<[email protected]>; 主题: Re: [OasisYang/SSG] I thinkYour code is taking up unnecessary 6GB memory in selftraining.py (#20) you don't need cluster_list on line 366,it takes up 6GB,beacuse cluster.components_ is a is a matrix shape of (15xxx,16552),you can see this in site-packages/sklearn/cluster/dbscan_.py. I think eps_list can have the same effect. I don't know if I am right, please tell me hello,Have you verified your conjecture? — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.
hi, I'm new to this. So I'm wondering what eps_list is and what you did in detail. By the way, I can't find cluster_list used on line 366 in selftraining.py, did I do something wrong?
Looking forward to your reply. May help a lot to me. Thank you very much.@okjer
from self-similarity-grouping.
作者改了代码,你debug一下代码就知道怎么做了
from self-similarity-grouping.
作者改了代码,你debug一下代码就知道怎么做了
非常感谢您的回答,但我确实是个小白,所以现在还是一头雾水
from self-similarity-grouping.
Related Issues (20)
- Error everywhere in the code; not working. Pls, Solve them and upload HOT 1
- something confused me in JointTrainer2
- something confused me in JointTrainer2
- How to do PK sampler to ensure the calculating of three triplet losses when the labels pf one image are different? HOT 4
- Seems a typo in the paper
- I ran into a problem when I tried to run source_train.py HOT 1
- Cannot obtain the reported performance by directly running the run.sh HOT 4
- Error while training with batch_size=32, double gpus, File "selftraining.py" HOT 4
- There might be a bug in line 195 of SSG-master/reid/trainers.py
- where is the script "source_train.py"?
- The generation of the pseudo labels.
- dataset写的比较难懂 HOT 1
- module 'reid.models' has no attribute 'create'
- TypeError: Can't instantiate abstract class Euclidean with abstract methods get_metric, score_pairs HOT 1
- where is source_train.py
- Can you share the trained model on the dataset of Market and Duke?
- SSG+&&SSG++
- ValueError: => No checkpoint found
- License question
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 self-similarity-grouping.