gosuto-inzasheru / aml-densenet-varying-learning-rates

Re-training the deep neural network DenseNet using various learning rate strategies. Entry for the Food Recognition Challenge for the Master's course Applied Machine Learning.

Geek Repo

Github PK Tool

deep-neural-networks densenet image-classification cyclical-learning-rate learning-rate-decay learning-rate-benchmarking

aml-densenet-varying-learning-rates

Food classification is a challenging problem due to the large number of food categories, since the visual similarity between different food categories is high. The goal is to build a model to predict the fine-grained food-category label given an image. This dataset contains 80 food categories indicated with a number.

About

Re-training the deep neural network DenseNet using various learning rate strategies. Entry for the Food Recognition Challenge for the Master's course Applied Machine Learning.

deep-neural-networks densenet image-classification cyclical-learning-rate learning-rate-decay learning-rate-benchmarking

Languages

Language:Jupyter Notebook 100.0%