Comments (5)
Thanks for your attention. The paches input is generated during the pre-training in
Line 18 in be066df
For UP-DETR, the model is pre-trained on ImageNet (by running main.py
) and fine-tuned on COCO (by running detr_main.py
).
For pre-training and fine-tuning code, we share the engine.py
file.
Please check https://github.com/dddzg/up-detr#unsupervised-pre-training for more details about how to pre-train UP-DETR on ImageNet.
You can try to read the code in datasets/selfdet.py
and models/updetr.py
for more details about the pre-training procedure.
from up-detr.
Feel free to re-open the issue if you have any other questions.
from up-detr.
from up-detr.
No. We expect the directory structure of the pre-training to be the following:
path/to/imagenet/
n06785654/ # caterogey directory
n06785654_16140.JPEG # images
n04584207/ # caterogey directory
n04584207_14322.JPEG # images
You can adjust the code in
Line 46 in be066df
to support coco2017 as the pre-training dataset.
from up-detr.
from up-detr.
Related Issues (20)
- Error in notebook while loading up-detr-coco-fine-tuned-300ep.pth HOT 2
- 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
- Evaluation problem
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.