معرفی شرکت ها
bayestorch-0.0.3
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشترتوضیحات
Lightweight Bayesian deep learning library for fast prototyping based on PyTorch
| ویژگی | مقدار |
|---|---|
| سیستم عامل | - |
| نام فایل | bayestorch-0.0.3 |
| نام | bayestorch |
| نسخه کتابخانه | 0.0.3 |
| نگهدارنده | [] |
| ایمیل نگهدارنده | [] |
| نویسنده | Luca Della Libera |
| ایمیل نویسنده | luca.dellalib@gmail.com |
| آدرس صفحه اصلی | https://github.com/lucadellalib/bayestorch |
| آدرس اینترنتی | https://pypi.org/project/bayestorch/ |
| مجوز | Apache License 2.0 |
# BayesTorch
[](https://www.python.org/downloads/)
[](https://github.com/lucadellalib/bayestorch/blob/main/LICENSE)
[](https://github.com/psf/black)
[](https://github.com/PyCQA/isort)
[](https://github.com/pre-commit/pre-commit)
[](https://pypi.org/project/bayestorch/)
Welcome to `bayestorch`, a lightweight Bayesian deep learning library for fast prototyping based on
[PyTorch](https://pytorch.org). It provides the basic building blocks for the following
Bayesian inference algorithms:
- [Bayes by Backprop (BBB)](https://arxiv.org/abs/1505.05424)
- [Markov chain Monte Carlo (MCMC)](https://www.cs.toronto.edu/~radford/ftp/thesis.pdf)
- [Stein variational gradient descent (SVGD)](https://arxiv.org/abs/1608.04471)
---------------------------------------------------------------------------------------------------------
## 💡 Key features
- Low-code definition of Bayesian (or partially Bayesian) models
- Support for custom neural network layers
- Support for custom prior/posterior distributions
- Support for layer/parameter-wise prior/posterior distributions
- Support for composite prior/posterior distributions
- Highly modular object-oriented design
- User-friendly and easily extensible APIs
- Detailed API documentation
---------------------------------------------------------------------------------------------------------
## 🛠️️ Installation
### Using Pip
First of all, install [Python 3.6 or later](https://www.python.org). Open a terminal and run:
```
pip install bayestorch
```
### From source
First of all, install [Python 3.6 or later](https://www.python.org).
Clone or download and extract the repository, navigate to `<path-to-repository>`, open a
terminal and run:
```
pip install -e .
```
---------------------------------------------------------------------------------------------------------
## ▶️ Quickstart
Here are a few code snippets showcasing some key features of the library.
For complete training loops, please refer to `examples/mnist` and `examples/regression`.
### Bayesian model trainable via Bayes by Backprop
```python
from torch.nn import Linear
from bayestorch.distributions import (
get_mixture_log_scale_normal,
get_softplus_inv_scale_normal,
)
from bayestorch.nn import VariationalPosteriorModule
# Define model
model = Linear(5, 1)
# Define log scale normal mixture prior over the model parameters
prior_builder, prior_kwargs = get_mixture_log_scale_normal(
model.parameters(),
weights=[0.75, 0.25],
locs=(0.0, 0.0),
log_scales=(-1.0, -6.0)
)
# Define inverse softplus scale normal posterior over the model parameters
posterior_builder, posterior_kwargs = get_softplus_inv_scale_normal(
model.parameters(), loc=0.0, softplus_inv_scale=-7.0, requires_grad=True,
)
# Define Bayesian model trainable via Bayes by Backprop
model = VariationalPosteriorModule(
model, prior_builder, prior_kwargs, posterior_builder, posterior_kwargs
)
```
### Partially Bayesian model trainable via Bayes by Backprop
```python
from torch.nn import Linear
from bayestorch.distributions import (
get_mixture_log_scale_normal,
get_softplus_inv_scale_normal,
)
from bayestorch.nn import VariationalPosteriorModule
# Define model
model = Linear(5, 1)
# Define log scale normal mixture prior over `model.weight`
prior_builder, prior_kwargs = get_mixture_log_scale_normal(
[model.weight],
weights=[0.75, 0.25],
locs=(0.0, 0.0),
log_scales=(-1.0, -6.0)
)
# Define inverse softplus scale normal posterior over `model.weight`
posterior_builder, posterior_kwargs = get_softplus_inv_scale_normal(
[model.weight], loc=0.0, softplus_inv_scale=-7.0, requires_grad=True,
)
# Define partially Bayesian model trainable via Bayes by Backprop
model = VariationalPosteriorModule(
model, prior_builder, prior_kwargs,
posterior_builder, posterior_kwargs, [model.weight],
)
```
### Composite prior
```python
from torch.distributions import Independent
from torch.nn import Linear
from bayestorch.distributions import (
CatDistribution,
get_laplace,
get_normal,
get_softplus_inv_scale_normal,
)
from bayestorch.nn import VariationalPosteriorModule
# Define model
model = Linear(5, 1)
# Define normal prior over `model.weight`
weight_prior_builder, weight_prior_kwargs = get_normal(
[model.weight],
loc=0.0,
scale=1.0,
prefix="weight_",
)
# Define Laplace prior over `model.bias`
bias_prior_builder, bias_prior_kwargs = get_laplace(
[model.bias],
loc=0.0,
scale=1.0,
prefix="bias_",
)
# Define composite prior over the model parameters
prior_builder = (
lambda **kwargs: CatDistribution([
Independent(weight_prior_builder(**kwargs), 1),
Independent(bias_prior_builder(**kwargs), 1),
])
)
prior_kwargs = {**weight_prior_kwargs, **bias_prior_kwargs}
# Define inverse softplus scale normal posterior over the model parameters
posterior_builder, posterior_kwargs = get_softplus_inv_scale_normal(
model.parameters(), loc=0.0, softplus_inv_scale=-7.0, requires_grad=True,
)
# Define Bayesian model trainable via Bayes by Backprop
model = VariationalPosteriorModule(
model, prior_builder, prior_kwargs, posterior_builder, posterior_kwargs,
)
```
---------------------------------------------------------------------------------------------------------
## 📧 Contact
[luca.dellalib@gmail.com](mailto:luca.dellalib@gmail.com)
---------------------------------------------------------------------------------------------------------
نیازمندی
| مقدار | نام |
|---|---|
| >=1.5.0 | torch |
| >=22.3.0 | black |
| >=2.3.1 | cibuildwheel |
| >=3.8.3 | flake8 |
| >=20.1.4 | flake8-bugbear |
| >=5.4.2 | isort |
| >=2.6.0 | pre-commit |
| >=3.2.0 | pre-commit-hooks |
| >=5.4.3 | pytest |
| >=2.9.0 | pytest-cov |
| >=3.3.0 | twine |
| >=5.4.3 | pytest |
| >=2.9.0 | pytest-cov |
زبان مورد نیاز
| مقدار | نام |
|---|---|
| >=3.6 | Python |
نحوه نصب
نصب پکیج whl bayestorch-0.0.3:
pip install bayestorch-0.0.3.whl
نصب پکیج tar.gz bayestorch-0.0.3:
pip install bayestorch-0.0.3.tar.gz