Maaliiik/Farmy-Potato-diseases-challenge

Winner of this challenge hosted by School of AI Algiers in collaboration with Farmy start-up. # Farmy-Potato-diseases-challenge Winner of this challenge hosted by School of AI Algiers in collaboration with Farmy start-up. # Potato challenge description: In this challenge, the objective is to train an image classification model able to perform well in production. For this reason, we extracted test data from the Farmy production data. Images included are submitted by farmers using the Farmy app. We selected the potato crop with two diseases (Early blight, Late blight) and a healthy class. I trained my classifies on available data such as academic datasets and images available on the internet in order to improve the F-score on the test images provided by Farmy. # Evaluation : -The evaluation metric for this competition is Accuracy. The accuracy is the most common evaluation metric for multi class classification. -Accuracy is one metric for evaluating classification models. Informally, accuracy is the fraction of predictions our model got right. Formally, accuracy has the following definition: -Accuracy = Correct predictions / the total number of predictions