No description, website, or topics provided.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
README.md
cnn_visualization.ipynb

README.md

CONVOLUTIONAL NEURAL NETWORKS:

Convolutional Neural Networks (ConvNets or CNNs) are a category of neural networks that have proven very effective in areas such as image recognition and classification. ConvNets have been successful in identifying faces, objects and traffic signs apart from powering vision in robots and self driving cars. CNNs use a variation of multilayer perceptrons designed to require minimal preprocessing. They are also known as shift invariant or space invariant artificial neural networks (SIANN), based on their shared-weights architecture and translation invariance characteristics. Convolutional networks were inspired by biological processes in which the connectivity pattern between neurons is inspired by the organization of the animal visual cortex. Individual cortical neurons respond to stimuli only in a restricted region of the visual filled known as the receptive field. The receptive fields of different neurons partially overlap such that they cover the entire visual field.CNNs use relatively little pre-processing compared to other image classification algorithms. This means that the network learns the filters that in traditional algorithms were hand-engineered. This independence from prior knowledge and human effort in feature design is a major advantage.

HOW CNN WORKS:

CNN make use of kernels to extract the features from images. kernels can be of any function used to capture the local dependencies in a image They uses convolution, pooling ,classification and non-linearity.

cnnimage

Visualization

Input

input

Heat Map

heatmap heatmap2

Visualize the Weights

weight

Visualize Activations

block1_conv1

block1

block1_conv2

block2

block2_conv1

block3

block3_conv1

block4

block4_conv1

block5

block5_conv3

block6

Read layer block5_conv3

readlayer

Bar Chart

barchart

Visualize the Gradients on the Input Image

gradient

Match Activations of Original Image

download