A small PyTorch library for Mixture Density Networks.
Project description
🎨 Mixture-Density-Nets
A small PyTorch library for Mixture Density Networks.
Install
simply run
pip install mixture-density-nets
Example
from mixture_density_nets import MDN, MDDistribution
# ....
mdn = MDN(in_dim, out_dim, n_components)
# ....
mu, sigma, lambda_ = mdn(net(input_data))
dist = MDDistribution(mu, sigma, lambda_)
loss = dist.nll(targets).mean()
# ...
samples, clusters = dist.sample(n=20) # draw 20 samples
For a more thorough example see example.ipynb.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for Mixture-Density-Nets-0.1.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | a14ef9b5cbaeb46f579334cd3b15417d5ebb3482e4142d9ce70a135fb9d593b9 |
|
MD5 | 740ab55914e76ec70cf96eca342e35d5 |
|
BLAKE2b-256 | a06e673a54c7766af0d19f21bd42cbc8af98d0118789400f192dfed652b27acb |
Close
Hashes for Mixture_Density_Nets-0.1.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | dac5a95f589be5d88318a744e0765fbbd0af19dd82de0a93b7cd1165ba7a261c |
|
MD5 | 0622c87b4cc1b4c554199f5782df7ee1 |
|
BLAKE2b-256 | 3f701abcae4f795b718dff08d80aa99cbeca0d989b7985ccdcfef06c84f110cc |