Issue about the dataset used in your code about bayesian-crowd-counting HOT 5 OPEN

@Yogurt2019
Thank you very much! According to the your answer, I found the meaning of keypoints[:, 2]: you can download the UCF-QNRF_ECCV18 dataset which used in this project & paper, then do a test for testing the function find_dis in preprocess_dataset.py, you will solve the problem!

from bayesian-crowd-counting.

Same question[1], but question[0] is easy.
Before training or testing, you should run the pre_process.py to pre-process the dataset from .mat to .npy.

from bayesian-crowd-counting.

@seekFire
Thx too! Keypoints[:, 2] represents the mean value of three nearest point distances.
都是**人本来想中文回复的，但是为了国外友人能看懂还是英文回复了
加油 :)

from bayesian-crowd-counting.

The last coordinate is the estimated sizes of people.

from bayesian-crowd-counting.

@seekFire
Thx too! Keypoints[:, 2] represents the mean value of three nearest point distances.
都是**人本来想中文回复的，但是为了国外友人能看懂还是英文回复了
加油 :)

I think this is not the nearest neighbor.
I tried the special case and got the following result.

k=np.asarray([0,1.1,2,13,44,5])
np.partition(k, 3)
array([ 1.1, 0. , 2. , 5. , 13. , 44. ])

from bayesian-crowd-counting.