PlantSeedlingClassification-Group13

Database: https://www.kaggle.com/c/plant-seedlings-classification/data the Sprint2 python script shows how we load and preprocess the Train Data and Test Data(Mask the train Data). In Sprint3, We extract the bottled-neck feartures using Xception Models from keras to improve the accuracy of the model. We use two models (logistic regression, a self-written CNN fully connected layers) to train the data we processed and we compare the results. In Sprint 4, we build a website for users to upload the images and return the species of the plant seedlings if available.