data reading speed

[acolijn]

So with the new data format we can read files quickly. I tried on a single file:

with h5py.File(file, 'r') as f:
group = f['events/']
data = {}
for name, dataset in group.items():
data[name] = np.array(dataset)

len(data)

Takes 0.6s to read 10k events. Time to modify event_reader.py

[cfuselli]

We need to adapt the functions in the model train files to use the new way of reading data