A method for visualizing the receiptive fields of a neural network
Project description
Force: A package to visualize the receptive fields
Force is a Python package that allows you to visualize the receptive fields of a neural network.
1. How to Run
To run this algorithm in Python:
from force.receptive_field import visualize_neuron
from gdbn.dbn import buildDBN
import matplotlib.pyplot as plt
# Make a deep belief network
dbn = buildDBN([1, 100, 1])
# Get the 3rd neuron on the 1st layer. (With Linear averaging)
neuron = visualize_neuron(dbn, 0, 2)
# Plot!
plt.imshow(neuron)
plt.show()
All configurable options are in the SBB/config.py file, in the variable CONFIG.
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
force-0.1.4.tar.gz
(2.0 kB
view details)
File details
Details for the file force-0.1.4.tar.gz
.
File metadata
- Download URL: force-0.1.4.tar.gz
- Upload date:
- Size: 2.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.12.1 pkginfo/1.4.2 requests/2.20.0 setuptools/39.1.0 requests-toolbelt/0.8.0 tqdm/4.28.1 CPython/2.7.15
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 1c9e1d9a645446a966354d993d2a05e4ab2d7951886e5db77657050e433f9365 |
|
MD5 | 0d244af3d06c4f0c863eece2d8833302 |
|
BLAKE2b-256 | fba039ea2701139d996272f81cc783eb461e198c33bb909a8d29a947e1a43b3b |