chensong1995 / E-CIR

Event-Enhanced Continuous Intensity Recovery (CVPR 2022)
MIT License
42 stars 2 forks source link

A question about the event_map. #6

Open chenkang455 opened 1 year ago

chenkang455 commented 1 year ago

Here is the code source: import os import torch import h5py import numpy as np hdf5_name = r"D:\Code\CV\Deblurring\E-CIR\data\REDS\train_0.hdf5" data = h5py.File(hdf5_name, 'r') idx = 0 event_map = data['event_map'][idx] print(event_map.max())

When running this code, the output is 11. I cannot understand the meaning of the output. Shouldn't it be 1,0 or -1? Thanks a lot if you could answer my question.

chensong1995 commented 1 year ago

Hello chenkang455,

Thanks for your interest in our work! event_map is the histogram of events instead of event polarities. This is the method that generates the histogram from raw events.

I hope this helps!

chenkang455 commented 1 year ago

Thanks a lot for your help!