Comments (21)
60 和 75 轮会降learning rate
https://github.com/layumi/AICIty-reID-2020/blob/master/pytorch/train_2020.py#L540
应该是正常的
from aicity-reid-2020.
60 和 75 轮会降learning rate
https://github.com/layumi/AICIty-reID-2020/blob/master/pytorch/train_2020.py#L540
应该是正常的
但都已经训练了30多个Epoch了,rank@5还不到90%,这也正常吗??
from aicity-reid-2020.
@郑博士 你好。我这边运行train+virtual数据集,当运行到40个Epoch的时候,太慢了,我把它停了,然后跑测试集,但结果rank@5才不到90%,mAP才0.35,这正常吗??会是哪里出错了呢??
你有这个比赛的数据集吗?
from aicity-reid-2020.
@郑博士 你好。我这边运行train+virtual数据集,当运行到40个Epoch的时候,太慢了,我把它停了,然后跑测试集,但结果rank@5才不到90%,mAP才0.35,这正常吗??会是哪里出错了呢??
你有这个比赛的数据集吗?
网上申请即可
from aicity-reid-2020.
@layumi 郑博士,我用真实数据集(也就是400个目标)进行训练,把80个Epoch都跑完了,但是mAP仍是只有0.47,请问这正常吗?
from aicity-reid-2020.
@s20163081161
是的。差不多。因为我validation用的gallery比较大。
之后你可以尝试post processing之类的,继续提升。
from aicity-reid-2020.
@s20163081161
是的。差不多。因为我validation用的gallery比较大。
之后你可以尝试post processing之类的,继续提升。
好的,多谢。
from aicity-reid-2020.
@s20163081161
是的。差不多。因为我validation用的gallery比较大。
之后你可以尝试post processing之类的,继续提升。
关于您所说的“gallery比较大”,我看您这里边的gallery是36900多张图片,那么多大的数量算大呢??有没有个衡量便准啥的??
from aicity-reid-2020.
@郑博士 你好。我这边运行train+virtual数据集,当运行到40个Epoch的时候,太慢了,我把它停了,然后跑测试集,但结果rank@5才不到90%,mAP才0.35,这正常吗??会是哪里出错了呢??
您好@s20163081161,请问您跑的测试集是怎么制作的?我看readme只讲了训练集的制作。谢谢!
from aicity-reid-2020.
from aicity-reid-2020.
您好@s20163081161,打扰了,我在网上申请并得到了所有数据集。您说的mAP的测试代码是submit.py还是test_2020.py?
from aicity-reid-2020.
from aicity-reid-2020.
test_2020.py。你跑的如何?
…
---原始邮件--- 发件人: "Hanwen Cao"<[email protected]> 发送时间: 2020年6月28日(周日) 晚上6:12 收件人: "layumi/AICIty-reID-2020"<[email protected]>; 抄送: "Mention"<[email protected]>;"s20163081161"<[email protected]>; 主题: Re: [layumi/AICIty-reID-2020] 测试所得mAP很低。 (#18) 您好@s20163081161,打扰了,我在网上申请并得到了所有数据集。您说的mAP的测试代码是submit.py还是test_2020.py? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.
抱歉,还没跑成功 :/
from aicity-reid-2020.
from aicity-reid-2020.
@layumi @s20163081161
I am running test_2020.py and as @layumi has mentioned earlier I am going to use val
for test.
But how could I use val
as a test dataset?
Should i split it to gallery
and query
?
Should I use val
dataset as gallery or both gallery
and query
?
from aicity-reid-2020.
@s20163081161 test_2020
is to verify the effectiveness of the model on validation ( no offical valid set, so I splitted ). The final test result is obtained by the submission to the official test website.
from aicity-reid-2020.
@martianvenusian
Test set is provided by the offical aicity organizer. If you want to verify the final result, please run submit_result.py
.
But they do not provide valid set, so I splitted the set to verify the model by using test_2020.py
from aicity-reid-2020.
@layumi Thank you for your support.
I have split val set to gallery
and query
as following if it is right way:
val/000341/
-- 000341_c010_7.jpg
-- 000341_c016_11.jpg
-- 000341_c017_5.jpg
query/000341/
-- 000341_c010_7.jpg
gallery/000341/
-- 000341_c016_11.jpg
-- 000341_c017_5.jpg
from aicity-reid-2020.
@郑博士 你好。我这边运行train+virtual数据集,当运行到40个Epoch的时候,太慢了,我把它停了,然后跑测试集,但结果rank@5才不到90%,mAP才0.35,这正常吗??会是哪里出错了呢??
你好,我想问一下在prepare_2020.py中生成的gallery这个文件夹,prepare_2020.py并没有向里面添加图片,但是在后面大量用到,这个文件夹是用来做什么的,谢谢
from aicity-reid-2020.
@layumi Thank you for your support.
I have split val set togallery
andquery
as following if it is right way:val/000341/
-- 000341_c010_7.jpg
-- 000341_c016_11.jpg
-- 000341_c017_5.jpgquery/000341/
-- 000341_c010_7.jpggallery/000341/
-- 000341_c016_11.jpg
-- 000341_c017_5.jpg
hello, could you please tell how to split the vaild set, which has query and gallery...
from aicity-reid-2020.
@郑博士 你好。我这边运行train+virtual数据集,当运行到40个Epoch的时候,太慢了,我把它停了,然后跑测试集,但结果rank@5才不到90%,mAP才0.35,这正常吗??会是哪里出错了呢??
您好@s20163081161,请问您跑的测试集是怎么制作的?我看readme只讲了训练集的制作。谢谢!
您好,请问gallery这个文件夹的数据是如何生成的呢?
from aicity-reid-2020.
Related Issues (20)
- cropped_aicity folder order??? HOT 1
- camera-aware model HOT 2
- 数据集问题 HOT 9
- mAP calculation HOT 1
- ff = torch.FloatTensor(n,512).zero_().cuda() HOT 1
- what is the mean of "gallery" in the test_2020.py file.
- 关于prepare_2020生成的gallery这个文件夹 HOT 4
- Cannot download feature extraction models HOT 4
- train_2020.py problem HOT 1
- where is SE_imbalance_s1_384_p0.5_lr2_mt_d0_b24+v+aug/opts.yaml HOT 5
- 训练问题 HOT 1
- 关于VeRi-776 应用的问题 HOT 5
- 使用arc loss训练,loss不收敛,acc较低。 HOT 1
- batch_size取24,一个steps运行492ms,这个正常吗?想知道作者一个steps的运算时间是多少 HOT 1
- train_2020.py运行后报错Couldn't find any class folder in ./data/pytorch2020/train HOT 4
- 可视化 HOT 1
- 请问这份代码的python和pytorch版本,以及其他重要包的版本,第一条评论请忽略
- --init_name pretrained model
- fine tuning 阶段用到的train_2020_ft.py似乎没有与论文描述一致:在前几个epoch中只更新classifier的参数
- 关于车辆特征提取的预训练模型 about pretrained model 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 aicity-reid-2020.