Comments (6)
Hi there, thanks for reaching out. Can you elaborate more details of your training settings (e.g. learning rate, pretrained model, epochs, and batchsize)? What's the accuracy you got?
from cvpr21chal-slr.
Yeah sure ,
I use Sign_Isolated_Conv3D_clip.py to run the code.
num_classes = 2000
epochs = 100
batch_size = 32
learning_rate = 1e-3
I also use the pretrained model that you provide but I train only the last layer (model.fc1 = nn.Linear(model.fc1.in_features, num_classes)).
The accuracy is about 10%
Thank you again
from cvpr21chal-slr.
I see. So I think you can try to train the whole network instead.
(load the pretrained model, pop the last fc layer, and append a new fc layer with 2000 classes)
For your reference, I trained the whole network and got 47.51% top-1 per-instance accuracy for RGB frames.
from cvpr21chal-slr.
Ok thank you for the info.
I also used gen_frames.py for data preprocessing and same sample_duration=32
Are you planning to provide code also for WLASL?
from cvpr21chal-slr.
I did the same thing for data preprocessing as well.
Yes, we are preparing a journal extension of this workshop paper.
A preprint version with code will be released shortly (targeting this month).
from cvpr21chal-slr.
I did the same thing for data preprocessing as well. Yes, we are preparing a journal extension of this workshop paper. A preprint version with code will be released shortly (targeting this month).
Already looked at your preprint version, and I've learned a lot from your current code. I am looking forward to your released code! Thank you for your share!
from cvpr21chal-slr.
Related Issues (20)
- Problem in directories provided in https://github.com/jackyjsy/CVPR21Chal-SLR/tree/main/SL-GCN HOT 1
- Problem in sign_gendata.py HOT 3
- Running Docker Command HOT 3
- Accuracy of V2 paper HOT 2
- the SL-GCN motion-related data prediction acc very low ? HOT 1
- Images' Docker HOT 3
- CUDA capability is not compatible with the current PyTorch installation HOT 1
- Train for bone HOT 2
- No such file or directory: 'final_models/val_rgb_final.pth' HOT 1
- How to get correct 'train_val_labels.pkl' ? HOT 2
- AUTSL dataset corrupted or in unknown format HOT 4
- gen_flow.py HOT 1
- Inference time calculation
- IndexError in forward func of Conv3D/Sign_Isolated_Conv3D_clip.py
- Help from an admirer
- RuntimeError: The size of tensor a (270) must match the size of tensor b (272) at non-singleton dimension 2
- Trouble running the Docker image
- Puzzle about HHA representation generation.
- Number Parameters
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 cvpr21chal-slr.