zju-vipa / kamalengine Goto Github PK
View Code? Open in Web Editor NEWKnowledge Amalgamation Engine
License: Apache License 2.0
Knowledge Amalgamation Engine
License: Apache License 2.0
Hello! I read the paper and want to implement the code, and I want to add some KA features on vit for image classification. My ideas are as below:
Provide a comprehensive and robust pipeline and a data preprocessing method that allows training with own datasets.
Implement KA on vision transformers to accomplish image classification tasks.(finetuned on several datasets such as Stanford Dogs)
Provide a multimodal transfer method to apply KA for audio classification.
Is this model not finished or what? I was trying the examples and there's been many mismatches of definitions.
For example
KamalEngine/kamal/slim/prunning/strategy.py", line 23, in
_PRUNABLE_MODULES= tp.DependencyGraph.PRUNABLE_MODULES
AttributeError: type object 'DependencyGraph' has no attribute 'PRUNABLE_MODULES'
Hi, thank you for sharing such an awesome project. I have some questions about the details in your code, and I sincerely hope you can help me solve them.
1 In your paper, it is said that "We conduct knowledge amalgamation for each block of TargetNet" (Section 5.1.1), however, in the code, it seems that you only apply the knowledge amalgamation on the decoder blocks. This makes me feel confused that whether we need to apply it on the encoder blocks, as in the "layerwise amal".
2 In the task branch code, should the object of student be JointSegNet, instead of BranchySegNet? As in BranchySegNet, the network does not use teacher's blocks.
Since after running the code on NYUv2, I only got a target net with mIOU 0.2830 by merging the depth model (RMSE: 0.6772) and the seg model (MIOU: 0.5227) with BranchySegNet. When I replace it with JointSegNet, I can get a target net with mIOU 0.5233.
I would really appreciate it if you could help me. Look forward to your reply, thanks!
请问有没有该模型使用步骤的详细说明?
Is there a link to the paper for the 4. Recombination algorithm (as seen in README)?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.