Skip to main content

Deep Neural Network Vizualizer

Project description

Vizdnn

Interpretable Deep Neural network is the next phase of understanding the working of neural network. This library suffices the need to vizualize neural network layer with simple python pip package.

Pip Install

pip install vizdnn

Use

from vizdnn import vizdnn 
import keras

visualize_neural_network = vizdnn(keras.applications.resnet.ResNet50() , "network_layer_name" , "test_image_name.jpg")

vis_layer = visualize_neural_network.get_layer()
visualize_neural_network.viz_feature_map(vis_layer)

Sample Viz

  • Sample test image

test-image-name.jpg


  • Vizualization from Resnet50 conv1_bn Layer.

Screenshot-from-2019-10-22-18-43-48.png


  • Vizualization from VGG16 block2_conv1 Layer.

Screenshot-from-2019-10-22-18-46-14.png


Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vizdnn-0.0.4.tar.gz (2.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

vizdnn-0.0.4-py3-none-any.whl (3.2 kB view details)

Uploaded Python 3

File details

Details for the file vizdnn-0.0.4.tar.gz.

File metadata

  • Download URL: vizdnn-0.0.4.tar.gz
  • Upload date:
  • Size: 2.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/2.0.0 pkginfo/1.5.0.1 requests/2.20.1 setuptools/41.4.0 requests-toolbelt/0.8.0 tqdm/4.19.1 CPython/3.6.8

File hashes

Hashes for vizdnn-0.0.4.tar.gz
Algorithm Hash digest
SHA256 7ebeee9dbc76b95837bd32f9ad5631914cd295d10b2a59b07949120bfa527b37
MD5 ac8e1d8c52db4f55d861e1ab0caa2426
BLAKE2b-256 4547fbc4fbbf86c986b7a685ca9f7d67725886315963ee8c5bd1417ac045bc14

See more details on using hashes here.

File details

Details for the file vizdnn-0.0.4-py3-none-any.whl.

File metadata

  • Download URL: vizdnn-0.0.4-py3-none-any.whl
  • Upload date:
  • Size: 3.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/2.0.0 pkginfo/1.5.0.1 requests/2.20.1 setuptools/41.4.0 requests-toolbelt/0.8.0 tqdm/4.19.1 CPython/3.6.8

File hashes

Hashes for vizdnn-0.0.4-py3-none-any.whl
Algorithm Hash digest
SHA256 bf4e8757832d76e89b6834678ff10210478e2f94d830b23b1966f90e75f83f78
MD5 669e11195b52fe92086ecb454088134c
BLAKE2b-256 de08ec529bf75e150695fe766851b093035c9cc85f7bc3fa4723c3f3c27e444c

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page