# pick a dataset
# it should not be a toy dataset (small dataset for learning)
# it shld be a standard dataset (large enough)
# should have enough variety (not simple cat and dog classification)
# shld not be too large (heavy gb data) <5gb 
# if working with large dataset use 10% sample

# dataset candidates
# https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia
# https://www.kaggle.com/moltean/fruits
# https://www.kaggle.com/alxmamaev/flowers-recognition
# https://www.kaggle.com/iarunava/cell-images-for-detecting-malaria
# https://www.kaggle.com/ikarus777/best-artworks-of-all-time
# https://www.kaggle.com/jessicali9530/celeba-dataset
# https://www.kaggle.com/meowmeowmeowmeowmeow/gtsrb-german-traffic-sign
# https://www.kaggle.com/grassknoted/asl-alphabet
# https://www.kaggle.com/puneet6060/intel-image-classification
# https://www.kaggle.com/kmader/siim-medical-images
# https://www.kaggle.com/paultimothymooney/breast-histopathology-images
# https://www.kaggle.com/andrewmvd/face-mask-detection

# celeb face recognition dataset
dataset_link = 'https://www.kaggle.com/jessicali9530/celeba-dataset'
backup_dataset_link =  'https://www.kaggle.com/alxmamaev/flowers-recognition'

pip install jovian --upgrade -q

import jovian