Preprocessing on the dataset

maheshkkumar / fscc

Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning (WACV 2020)

https://arxiv.org/abs/2002.00264

MIT License

24 stars 1 forks source link

Preprocessing on the dataset #3

Closed zzpustc closed 3 years ago

zzpustc commented 3 years ago

Hi,

Great application of MAML. I wonder if you haven't released some preprocessing operations. I found I cannot directly run the code, The original dataset has not been divided into 'tasks (classes)', so I will get errors in the get_task.py. Hope to hear from you.

Best.

maheshkkumar commented 3 years ago

Hi,

Please refer to #4 for the directory structure to create train and test scenes. We refer to the crowd scenes as either tasks or classes.