Closed theseventhflow closed 4 years ago
Hi,
Sure. It is feasible if you want to keep all the possible pairs/groups to the training data. Generally speaking (in my personal opinion), if you use more training data, you can get better final results. Although I think the data I have not used is only a small fraction of the training data, you can still try it by yourself!
Thanks, Remy
Hi, thanks for your reply. I will try to feed more data.
Sorry for asking this years later but. Do you know which parameter should be changed to feed more data? Will changing group_size from 5 to for example 4 feed more data?
Hi, your work is really amazing! I have some questions about the def prepare_data() function in line 252. `
# abandon the last
for i in np.arange(0, len(pairs)-self.group_size, self.group_size*2): data = pairs[i:i+self.group_size] if len(data) == self.group_size: segments.append(data) `
Thank you!