abhijeet3922 / food-classification-task-transfer-learning

The application demonstrates the advantage of using transfer learning for smaller datasets. Food-11 is a small dataset with 11K images for 11 categories of food. It uses features learnt by already trained VGG16 on large Imagenet data to train a classifier for Food Classification Task..

Food-Classification-Task-Transfer-learning

The application demonstrates the advantage of using transfer learning for smaller datasets. Food-11 is a small dataset with 11K images for 11 categories of food. It uses features learnt by already trained VGG16 on large Imagenet data to train a classifier for Food Classification Task.

food-classification-task-transfer-learning's Issues

Is it full data or partial one?

When I run this command...
len(train),len(val),len(test)

I get less number of results compared to your github repo.
(3001, 1001, 1001)
Your count:
(9866, 3430, 3347)

It means the data made available on dropbox is not complete. And therefore probably I get this error as well...

train_y = [int(img.split("/")[-1].split("_")[0]) for img in train]
ValueError: invalid literal for int() with base 10: '.DS'

Please let me know how to download the complete dataset and how to deal with above error.