Comments (3)
I found the issue you describe above occurs in pytorch version 1.13.1, so I guess it is caused by the different pytorch version (I use pytorch1.9.0), maybe the up-to-date version of pytorch has disabled the indices operation on different devices of L17 in metrics.py.
To fix this, I suggest that you add a .cpu() function after the indices to transfer them to the cpu, as the minimum modification solution. Like this:
pred_labels = g_pids[indices.cpu()]
And I will add this adaptation code in next commit.
from irra.
I am sorry that our code is confusing you, the presence or absence of the .cpu() operation is irrelevant in (L85) code. This is because qids, gidsy are always on the CPU and the calculated CMC and mAP are all on the CPU.
Anyway, thank you for pointing this out and we have modified the potentially misleading code at L85.
from irra.
First, the modification that I pointed in my issue made the rank
function crashing. I do not have access to my computer so I cannot provide the error message right now. I will provide the error message as soon as possible. If you do not have the error message it's, maybe, because I use a recent torch version? In brief, if I do not send IDs on GPU then I cannot evaluate the epoch with itc
loss. Also, I will test the updated code with my laptop and get you up to date.
Second, your repo is clean code. I read most of your 3k lines and I can tell your code has a good quality, in addition of good research findings. Thanks again for your quick answers and your sharing.
from irra.
Related Issues (20)
- How to Solve multi-GPU Training Problems? HOT 1
- Multi gpu training problem HOT 2
- Is it unfair to use a pre-trained CLIP model compared to some other methods in Table 1?
- PROBLEMS REGARDING DIFFRENT SPIT OF DATASET
- The id loss in the table is not a separate loss, but is trained jointly with the itc loss in the baseline.
- KeyError: 'mlm_ids'
- 文本全局特征如何获得? HOT 2
- There is a mistake that the mlm module that the mask token's output and the whole token HOT 1
- How to specify a particular GPU to train? HOT 1
- a small bug about RSTPReid dataset HOT 2
- Maybe an error
- Maybe an error in the original paper? HOT 1
- CUHK-PEDES HOT 7
- 请问谁有ICFG-PEDES数据集,救救孩子,发邮件给作者三天了也没有回复 HOT 12
- The nan error HOT 1
- 想问一下想得到主观结果是运行哪个文件呢 HOT 1
- Confusion about the IRR module HOT 1
- Are training the CLIP model from scratch? or are you using the pretrained weights? HOT 1
- 如何使用多GPU训练? HOT 6
- visualize.py HOT 3
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 irra.