CIFAR Image Classification

Contributors

Evan Otero & Shikun (Jason) Wang

About

Classifying images from the CIFAR-10 dataset using a convolutional neural network. The images need to be normalized and the labels need to be one-hot encoded. The project will require building a convolutional, max pooling, dropout, and fully connected layers. At the end, we will see our neural network's predictions on the sample images.

Network Graph

#ResNet Model #[ResNet-50] (http://ethereon.github.io/netscope/#/gist/db945b393d40bfa26006)

Summary Data

Accuracy

Cross Entropy

Convolutional Layer 1

Weights

Biases

Activations

Convolutional Layer 2

Weights

Biases

Activations

Resources

https://github.com/udacity/deep-learning/tree/master/image-classification