shyamsn97 / hyper-nn Goto Github PK
View Code? Open in Web Editor NEWEasy Hypernetworks in Pytorch and Jax
License: MIT License
Easy Hypernetworks in Pytorch and Jax
License: MIT License
Hi Shyam! Thanks for providing the easy-to-use wrapper for hypernetworks, it's amazing!
One question: The parameters are generated by function generate_params
hyper-nn/hypernn/torch/linear_hypernet.py
Lines 56 to 61 in 2765728
Thus the starting points are always random embeddings, right? If I want to make use of the input data x
also as the input of hypernetwork, what should I do? Could you please kindly outline a bit?
Hi, I was trying out the notebook examples and came across the following issue with hyper-nn==0.2.2
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
[<ipython-input-3-445f86a0d085>](https://localhost:8080/#) in <module>
62 NUM_EMBEDDINGS = 32
63
---> 64 hypernetwork = MultiTaskHypernetwork.from_target(
65 num_tasks = NUM_TASKS,
66 target_network = target_network,
1 frames
[<ipython-input-3-445f86a0d085>](https://localhost:8080/#) in __init__(self, num_tasks, target_network, num_target_parameters, embedding_dim, num_embeddings, weight_chunk_dim)
16 ):
17 self.num_tasks = num_tasks
---> 18 super().__init__(
19 target_network = target_network,
20 num_target_parameters = num_target_parameters,
TypeError: __init__() got an unexpected keyword argument 'embedding_dim'
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.