Comments (4)
Do not replace the full back
Thank you so much for your reply! I was also planning to use another object detection model. hope I get better results soon thanks again!
from scene-graph-benchmark.pytorch.
Hi @narchitect ,
The mAP you are referring to here is the performance of your object detection alone (i.e. bounding box regression + classification), I would suggest you to switch from Faster-RCNN to another detector which will be more performant for few-shot settings, which seems to be your case. Faster-RCNN is a pretty old and bad detector at this point, especially for few-shot, using a more recent detector pretrained on a larger dataset such as Swin transformer, DETR, ViT etc will be better.
Then you can train a SGGen model by freezing the weights of your object detector and replacing the RPN layers, as I explained it in here.
Do not replace the full backbone layers or you will have to change the features extractor as well, which is more complex.
from scene-graph-benchmark.pytorch.
Hi @narchitect ,
The mAP you are referring to here is the performance of your object detection alone (i.e. bounding box regression + classification), I would suggest you to switch from Faster-RCNN to another detector which will be more performant for few-shot settings, which seems to be your case. Faster-RCNN is a pretty old and bad detector at this point, especially for few-shot, using a more recent detector pretrained on a larger dataset such as Swin transformer, DETR, ViT etc will be better. Then you can train a SGGen model by freezing the weights of your object detector and replacing the RPN layers, as I explained it in here. Do not replace the full backbone layers or you will have to change the features extractor as well, which is more complex.
How to freeze the weight of your object detector and how to implement the code
from scene-graph-benchmark.pytorch.
Hi @narchitect ,
The mAP you are referring to here is the performance of your object detection alone (i.e. bounding box regression + classification), I would suggest you to switch from Faster-RCNN to another detector which will be more performant for few-shot settings, which seems to be your case. Faster-RCNN is a pretty old and bad detector at this point, especially for few-shot, using a more recent detector pretrained on a larger dataset such as Swin transformer, DETR, ViT etc will be better. Then you can train a SGGen model by freezing the weights of your object detector and replacing the RPN layers, as I explained it in here. Do not replace the full backbone layers or you will have to change the features extractor as well, which is more complex.How to freeze the weight of your object detector and how to implement the code
How to freeze the weights depends on your detector, however here you can do something simpler by forcing your detector to be in eval mode with something like model.rpn.eval()
or model.backbone.eval()
somewhere before your training loop, to ensure no gradients are computed.
from scene-graph-benchmark.pytorch.
Related Issues (20)
- Large difference in the accuracy of detection model
- PredCls, SGCls for custom images HOT 1
- RuntimeError about demo! HOT 2
- Dense Representation Extraction
- When I modified rel_dists in the relationship prediction section_ After dists, all model parameters cannot be read and are displayed as nan
- VGG-16 as backone
- VGG-16 as backbone,BUG!!!
- why predcls R@100 needs to be 75%?
- Model fails (does not start) to classify custom image HOT 16
- Use my own object detection model instead of Faster-RCNN HOT 2
- SGDet on Custom Images HOT 8
- Reported metrics' results are calculated on eval or test set? HOT 1
- ModuleNotFoundError: No module named 'yacs'
- AssertionError: Invalid type <class 'NoneType'> for key TO_TEST HOT 1
- cudaErrorAssert: device-side assert triggered
- Replace backbone
- Error when installing maskrcnn_benchmark HOT 17
- SGDet model can't train
- Multi-card GPUs can't train occupancy will be 100 card masters, single GPUs won't.
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 scene-graph-benchmark.pytorch.