1. Rethinking the Inception Architecture for Computer Vision Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, Zbigniew Wojna https://arxiv.org/pdf/1512.00567v3
2. Very Deep Convolutional Networks for Large-Scale Image Recognition Karen Simonyan, Andrew Zisserman https://arxiv.org/pdf/1409.1556
https://www.kaggle.com/adinishad/tomato-leaf-detection-by-transfer-learning/data
- VGG19
- InceptionV3
- No. of classes: 10
- Classes :- ['Tomato___Late_blight' , 'Tomato___healthy' , 'Tomato___Early_blight' , 'Tomato___Septoria_leaf_spot' , 'Tomato___Tomato_Yellow_Leaf_Curl_Virus' , 'Tomato___Bacterial_spot' , 'Tomato___Target_Spot' , 'Tomato___Tomato_mosaic_virus' , 'Tomato___Leaf_Mold' , 'Tomato___Spider_mites Two-spotted_spider_mite']
- loss: 0.3708
- accuracy: 0.9639
- val_loss: 4.1287
- val_accuracy: 0.8198
- loss: 0.0531
- accuracy: 0.9804
- val_loss: 0.2975
- val_accuracy: 0.9210
- Deployed it as a web application using Flask.
- python==3.7
- Flask==1.1.2
- numpy==1.18.4
- tensorflow==2.2.0
- Werkzeug==1.0.1
- Pycharm
- Google Colab
- git
- Flask