Skip to content

hasit73/CNN-feature-map-generation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

CNN-Feature-Map-Generation

Backend : Tensorflow

Library required:

  • opencv = '4.5.4-dev'
  • matplotlib='3.3.4'
  • tensorflow='2.6.0'
  • tqdm='4.62.3'

Quick Overview about structure

1) map_generation.py

  • Loading model and user configurations
  • generate feature map for input image and save feature map

2) map_gen.ipynb

  • this file contains just a sample piece of code
  • feature map generation code

How to use

  1. clone this directory

  2. use following command to run feature map generation on your input image

python main.py -m <model_name> -d <depth_value> -i <source_image>

Ex:

python main.py -m resnet50 -d 5 -i sample.png

Results

feature map samples

vgg_conv2_block1_preact_bn_FusedBatchNormV3_0

vgg_conv2_block1_preact_relu_Relu_0

About

here i am using tensorflow framework to work with pre trained model and will checkout how feature maps are generated in cnn model.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published