An open API service indexing awesome lists of open source software.

https://github.com/camara94/visualizing-filters-cnn-tensorflow

Welcome to Visualizing Filters of a CNN using TensorFlow. This is a project-based course which should take less than 1 hours to finish. Before diving into the project, please take a look at the course objectives and structure:
https://github.com/camara94/visualizing-filters-cnn-tensorflow

cnn cnn-keras deep-learning gradient-descent logic-programming machine-learning tensorflow

Last synced: 2 months ago
JSON representation

Welcome to Visualizing Filters of a CNN using TensorFlow. This is a project-based course which should take less than 1 hours to finish. Before diving into the project, please take a look at the course objectives and structure:

Awesome Lists containing this project

README

          

# Visualizing Filters CNN Tensorflow

Welcome to Visualizing Filters of a CNN using TensorFlow. This is a project-based course which should take less than 1 hours to finish. Before diving into the project, please take a look at the course objectives and structure:

## Course Objectives

In this course, our primary learning objective is to visualize image features that maximally activate filters of a **CNN**.

## Course Structure

This course is divided into 3 parts:

1. Course Overview: This introductory reading material.

2. **Visualizing Filters of a CNN using TensorFlow**: This is the hands on project that we will work on in Rhyme.

3. Graded Quiz: This is the final assignment that you need to pass in order to finish the course successfully.

## Project Structure

The hands on project on **Visualizing Filters of a CNN using TensorFlow** is divided into following tasks:

**Task 1: Introduction**
**Task 2: Downloading the Model**
**Task 3: Get Submodels**
**Task 4: Image Visualization**
**Task 5: Training Loop**
**Task 6: Final Results**

## Link

[https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet1k_b3/feature_vector/2](https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet1k_b3/feature_vector/2)