### Install pymoten using pip

Source: https://github.com/gallantlab/pymoten/blob/main/docs/source/index.md

Install the latest version of pymoten from GitHub or the most recent release from PyPI.

```bash
pip install git+https://github.com/gallantlab/pymoten.git
```

```bash
pip install pymoten
```

--------------------------------

### Install Latest PyMoten Release

Source: https://github.com/gallantlab/pymoten/blob/main/README.rst

Install the most recent stable release of PyMoten from PyPI using pip.

```bash
pip install pymoten
```

--------------------------------

### Install PyMoten from GitHub

Source: https://github.com/gallantlab/pymoten/blob/main/README.rst

Install the latest version of PyMoten directly from its GitHub repository using pip.

```bash
pip install git+https://github.com/gallantlab/pymoten.git
```

--------------------------------

### Enable GPU acceleration with PyTorch

Source: https://github.com/gallantlab/pymoten/blob/main/docs/source/index.md

Switch to a GPU backend (torch_cuda or torch_mps) for faster computation. This requires PyTorch to be installed. The stimulus is moved to the GPU, projected, and then converted back to NumPy.

```python
import moten
from moten.backend import set_backend

# Switch to a GPU backend (returns the backend module)
backend = set_backend("torch_cuda")

pyramid = moten.get_default_pyramid(vhsize=(vdim, hdim), fps=24)

# Move the stimulus onto the GPU, project, then bring the result back
stimulus_gpu = backend.asarray(luminance_images)
moten_features = pyramid.project_stimulus_batched(stimulus_gpu)
moten_features = backend.to_numpy(moten_features)
```

--------------------------------

### Build Pymoten Website

Source: https://github.com/gallantlab/pymoten/blob/main/docs/README.md

Commands to navigate to the docs directory, build the website, and open it in Firefox.

```bash
cd docs
make githubio-docs
firefox build/html/index.html
```

--------------------------------

### Pymoten Website Requirements

Source: https://github.com/gallantlab/pymoten/blob/main/docs/README.md

Lists the Python packages required to build the Pymoten website.

```bash
numpydoc
sphinx
sphinx_gallery
sphinx_bootstrap_theme
```

--------------------------------

### Compute motion energy features from a video file

Source: https://github.com/gallantlab/pymoten/blob/main/docs/source/index.md

Stream a video file, convert it to luminance images, and compute motion energy features using a Gabor filter pyramid.

```python
import moten

# Stream and convert the RGB video into a sequence of luminance images
video_file = 'http://anwarnunez.github.io/downloads/avsnr150s24fps_tiny.mp4'
luminance_images = moten.io.video2luminance(video_file, nimages=100)

# Create a pyramid of spatio-temporal gabor filters
nimages, vdim, hdim = luminance_images.shape
pyramid = moten.get_default_pyramid(vhsize=(vdim, hdim), fps=24)

# Compute motion energy features
moten_features = pyramid.project_stimulus(luminance_images)
```

--------------------------------

### Compute motion energy features from synthetic data

Source: https://github.com/gallantlab/pymoten/blob/main/docs/source/index.md

Generate synthetic video data and compute motion energy features using a default Gabor filter pyramid.

```python
import moten
import numpy as np

# Generate synthetic data
nimages, vdim, hdim = (100, 90, 180)
noise_movie = np.random.randn(nimages, vdim, hdim)

# Create a pyramid of spatio-temporal gabor filters
pyramid = moten.get_default_pyramid(vhsize=(vdim, hdim), fps=24)

# Compute motion energy features
moten_features = pyramid.project_stimulus(noise_movie)
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.