We have used Resnet 50 for image classification.
Built Basic Classifier with MATLAB.
The network has an image input size of 224-by-224-by-3.
This Requires MATLAB (R2018b and above) and the Deep Learning Toolbox.
This NN have three functions:
- resnetLayers: Creates an untrained network with the network architecture of ResNet-50
- assembleResNet: Creates a ResNet-50 network with weights trained on ImageNet data
- Predict: Demonstrates how to classify an image using a trained ResNet-50 network