Comments (2)
These results can simply be explained by the fact that freezing and unfreezing was only implemented for ResNet50 and not for other architectures (my bad). That’s why the other backbones gave such a bad accuracy. The non-pretrained weights of the model (1x1 conv layer and prototypes) need to settle in a bit before finetuning the backbone. I have updated the code such that every network first trains the add-on layer and prototypes for a few epochs, before unfreezing and training the whole model. Secondly, since the backbone is pretrained on a task which is further away from the target task (not iNat but ImageNet for bird recognition), it makes sense to increase the learning rates of the backbone. I didn’t do any hyperparameter tuning, but something like
python3 main_tree.py --epochs 150 --log_dir ./runs/protoree_cub --dataset CUB-200-2011 --lr 0.001 --lr_block 0.002 --lr_net 1e-4 --num_features 256 --depth 9 --net resnet50 --freeze_epochs 2 --milestones 60,80,100,120,140
should work much better than reported before (I got 71% for ResNet50 and 54% for VGG16). The results will probably not match the iNat-initialization, since CUB-200-2011 is a very small dataset and therefore susceptible to good weight initializations which wasn’t the core focus for now.
from prototree.
Thanks a lot M-Nauta!
from prototree.
Related Issues (14)
- Upsample issue multiple bounding boxes HOT 1
- is finetuning avaliable? HOT 1
- Model inference question
- connect to swin transformer
- Why is the preprocessed Stanford cars dataset only consisting of training set and testing set without projecting set, nor does it have a train_crop?
- Using proto tree for multi label classification HOT 1
- Training time HOT 3
- My final acc is only 76% HOT 2
- Acc lower than paper claims HOT 4
- Projection of prototypes HOT 1
- The requested URL /internal/car196/cars_train.tgz was not found on this server. HOT 1
- Model can not be loaded HOT 1
- Accuracy of Prototree ensemble 5 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 prototree.