API to compose PyTorch neural networks on the fly.
Project description
Torch-Nets
Compose PyTorch neural networks with ease.
Installation
From PYPI (current version: v0.0.1
)
pip install torch-nets
Alternatively, install the development version from GitHub:
git clone https://github.com/mvinyard/torch-nets.git;
cd torch-nets; pip install -e .
Example API use-case
from torch_nets import TorchNet
Create a feed-forward neural network
net = TorchNet(
in_features=50,
out_features=50,
hidden=[400, 400],
activation="LeakyReLU",
dropout=0.2,
n_augment=0,
bias=True,
output_bias=True,
)
net
Sequential(
(hidden_1): Sequential(
(linear): Linear(in_features=50, out_features=400, bias=True)
(dropout): Dropout(p=0.2, inplace=False)
(activation): LeakyReLU(negative_slope=0.01)
)
(hidden_2): Sequential(
(linear): Linear(in_features=400, out_features=400, bias=True)
(dropout): Dropout(p=0.2, inplace=False)
(activation): LeakyReLU(negative_slope=0.01)
)
(output): Sequential(
(linear): Linear(in_features=400, out_features=50, bias=True)
)
)
The only required arguments are in_features
and out_features
. The network can be made as simple or complex as you want through optional parameters.
Potential future plans
- Composition of
torch.optim
funcs.
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
torch-nets-0.0.2rc0.tar.gz
(18.7 kB
view hashes)
Built Distribution
Close
Hashes for torch_nets-0.0.2rc0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d1ee478548c2d5f13f95f4d11b07633a57f37113baa60e9e875e70e19f412915 |
|
MD5 | 453da7866facecfd0f72aa5321a15457 |
|
BLAKE2b-256 | 35630f932166133f10328186590f87a38249f6f9fcf550198fe3cb5520c6e8ec |