Comments (2)
In fact, I have did similar experiments before. However, it did not obtain better performance (basically unchanged), and slowed down the training speed. In the novel-finetuning stage, it is not that the more trainable parameters the better. So I chose to freeze the parameters of RCNN-Head. But if you have other ideas, I think it is completely possible to make this part of the parameters trainable. Hope it helps!
from defrcn.
After the base class is trained, the final classification layer and regression layer of roi head are reinitialized. In the novel-finetuning stage, did you only train them, and the other parameters were frozen? Is this operation consistent with the TFA paper? Thank you!
from defrcn.
Related Issues (20)
- How can I customize new hyperparameters in detectron2
- argument 'alpha' must be Number, not NoneType HOT 2
- 可视化
- AssertionError: Checkpoint checkpoints/voc/mydefrcn/defrcn_det_r101_base1/model_reset_remove.pth not found! HOT 6
- Why the different number of images on inference?
- How to reproduce the results in Figure4(b)? HOT 1
- Help with multi-GPU training in Google Colab HOT 1
- Guide on Fine Tuning
- TypeError: init() got an unexpected keyword argument 'first_stride' HOT 2
- Where is pascal VOC metasplit located?
- Out of memory error during evaluation but training works fine! HOT 3
- running Inference on model
- Why final checkpoint is removed in run_voc.sh script? HOT 1
- Do we need to give support image during inference? HOT 1
- cuda version HOT 2
- About the fine tune problems
- main.py: error: unrecognized arguments: --opts MODEL.WEIGHTS /public/home/jd_fky/project/DeFRCN/data/ImageNetPretrained/MSRA/R-101.pkl OUTPUT_DIR checkpoints/coco/defrcn/defrcn_det_r101_base 3 I don't know why running main.py causes this problem HOT 1
- fine-tuning on my cutsomized dataset
- OutOfMemoryError with PrototypicalCalibrationBlock HOT 5
- RuntimeError: CUDA error: no kernel image is available for execution on the device
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 defrcn.