This course teaches learners how to train a convolutional neural network using Tensorflow & Keras to classify images of rock, paper, & scissors. The course covers setting up the environment, data preparation, network training, CNN approaches, GPU utilization for faster training, hyperparameter tuning with Kerastuner, model saving/loading, image plotting, and image format conversion. The intended audience for this course is individuals interested in image classification using neural networks.
Real-World Python Neural Nets Tutorial - Image Classification with CNN - Tensorflow & Keras
Keith Galli via YouTube
Overview
Syllabus
Video Overview
Getting Started Setup & Installation
Finding datasets to use
Data Preparation
Additional Data Prep Convert data to NumPy format
Reshape Data & Normalize values between 0-1
Train our first network to classify images
Convolutional Neural Net CNN approach
Using GPU on Google Colab speed up training
Improving our CNN reduce image size, max pooling, dropout, etc
Using Kerastuner to automatically pick best hyperparameters
Save & Load our models
Plot NumPy arrays as images
Convert JPG/PNG images to NumPy
Final thoughts
Taught by
Keith Galli
Related Courses
-
Classification of COVID19 using Chest X-ray Images in Keras
-
Keras with TensorFlow Course - Python Deep Learning and Neural Networks for Beginners Tutorial
-
Image Classification with CNNs using Keras
-
Traffic Sign Classification Using Deep Learning in Python/Keras
-
Visualizing Filters of a CNN using TensorFlow
-
Image Modeling with Keras
