get_data() in O'Reilly Training.ipynb make kernel issues

[ccqpein]

I use docker to run Caption this, with TensorFlow. I followed everything in readme and when I run feats, captions = get_data(annotation_path, feature_path) Jupyter show alart that "The kernel appears to have died. It will restart automatically" everytime.

Do I miss something? How could I fix this issue?

Thank you!

[raulpuric]

Ahh my apologies.
When I was trying to train, a set of preloaded weights I removed the memory mapping from the call to np.load(...) to speed up IO. The docker container (and some laptops too) does not have enough memory to load the features which sits at ~5.9 GB. I've added back the memory map in the most recent commit.