Comments (14)
The last epoch:
IoU metric: bbox
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.432
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.632
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.458
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.209
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.475
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.622
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.342
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.550
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.589
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.311
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.650
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.816
Training time 7 days, 12:19:43
The highest at epoch 288:
IoU metric: bbox
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.435
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.633
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.464
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.211
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.477
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.626
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.342
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.550
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.589
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.315
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.653
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.818
from up-detr.
Still running, it looks good this time.
from up-detr.
0.435
from up-detr.
May I ask you for the detail config of training coco (number of gpus and etc)?
There is a log in our experiments:https://drive.google.com/file/d/1DQqveOZnMc2VaBhMzl9VilMxdeniiWXo/view?usp=sharing
You can compare your log with it.
from up-detr.
GPU using 8 cards of V100 , and the commands are the same as your provided in the github.
Is there anything has to be modified before running the train program?
from up-detr.
I check it again. There is a mistake of my script. I am so sorry. The lr_backbone
should set to 5e-5
instead of 5e-4
. I will update the README. Thanks a lot! I will keep the issue open until you get the right result.
from up-detr.
Hi @rock4you , may I ask for some new progress?
from up-detr.
The AP of coco val2017 with 300 epochs in Table 2 of the paper is 42.8,
is this result get from a certain training process or the mean value of several times ?
from up-detr.
As coco dataset is large, the result is reported at the last training epoch without serveral times (I guess the result variance is small on coco). BTW, may I ask for your result?
from up-detr.
Still running, the AP around epoch 240 is 0.430.
The training speed is about 40 epochs / day
from up-detr.
Glad to hear the result. As far as I observe, the open-source pre-trained model is a little better than paper report.
from up-detr.
👍🏻 👍🏻
from up-detr.
Nice to hear the result. Could you attach more detailed COCO style evaluation result (such like https://gist.github.com/dddzg/cd0957c5643f5656f6cdc979da4d6db1)?
from up-detr.
I check it again. There is a mistake of my script. I am so sorry. The
lr_backbone
should set to5e-5
instead of5e-4
. I will update the README. Thanks a lot! I will keep the issue open until you get the right result.
Hi you mean in the finetune stage or pretrain stage ? Why in the pretrain stage the backbone should freeze ?
from up-detr.
Related Issues (20)
- A blog about UP-DETR HOT 6
- Error in notebook while loading up-detr-coco-fine-tuned-300ep.pth HOT 2
- Some questions about your code HOT 5
- Questions about the multi-query patch model HOT 1
- bounding boxes shift problem
- How extract precision, recall and f1-score metrics HOT 1
- Code for VOC HOT 2
- detectiong objects HOT 1
- Class Loss HOT 2
- SWAV HOT 1
- Random Crop HOT 2
- num_classes HOT 6
- How to support batch learning for one-shot object detection training? HOT 8
- Getting access to the one-shot object detection training code
- 请问如何在coco上预训练?
- backbone的build时会构建position embeding,需要用到nestedtensor的mask,请问输入tensor类型的patch不会报错吗
- 请问是否可以开源one-shot部分的训练代码
- Unexpected key(s) in state_dict: "feature_align.layers.0.weight", "feature_align.layers.0.bias", "feature_align.layers.1.weight", "feature_align.layers.1.bias", "patch2query.weight", "patch2query.bias". HOT 1
- 请问微调300个epoch能收敛吗?为什么我在自己数据集微调了600个批次都收敛不了 HOT 1
- _IncompatibleKeys 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 up-detr.