📈 Data Science Challenge on Nuwe
The data science challenge will consist in creating an image classification model, which from a given dataset, predicts what type of deforestation appears in the image with the objective of early detection of this type of actions in protected lands.
The following resources will be provided to complete the challenge:
A training 'csv' files that relate the ID of the images to their features and classes.
A testing 'csv' files that relate the ID of the images to their features.
A zip file containing a few thousand training and testing images. This zip file has a weight of 309MB.
No infrastructure will be provided to train the models, so you can do it locally or as you prefer.
The challenge will be to create an image classification model and train it with the training images we provide, once you find the model that maximizes the f1-score, you will have to apply your model to classify the testing images. Your score will depend on the F1-score of your model with the test images, the quality of your code and the explanation of the solution you provide.