VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION. Karen Simonyan∗ & Andrew Zisserman +
Visual Geometry Group, Department of Engineering Science, University of Oxford {karen,az}@robots.ox.ac.uk
https://arxiv.org/pdf/1409.1556.pdf
https://www.kaggle.com/alxmamaev/flowers-recognition
- VGG16
- MobileNetV2
- Self created 5 CNN models
- No. of classes: 5
- loss: 0.0066
- accuracy: 1.0000
- val_loss: 0.7674
- val_accuracy: 0.8125
- Deployed it as a web app using Flask.
- Flask==1.1.2
- numpy==1.18.4
- tensorflow==2.2.0
- Werkzeug==1.0.1
- Pycharm
- Google Colab
- git