This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# sid rajaram | |
import numpy as np | |
import time | |
# This approach assumes there are class scores in the incoming lists as well. | |
# Selects best score and then suppresses. | |
# class score + bounding box = (p, x, y, w, h) | |
# p: classification score / probability | |
# x,y: location | |
# w,h: dimensions |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# 3D Non-Maximum Suppression Implemented in Python - Sidharth Rajaram | |
import numpy as np | |
import time | |
# This approach assumes there are prediction scores (one class only) in the incoming bounding boxes as well. | |
# Selects best score and then suppresses. | |
# class score + bounding box = (p, x, y, z, w, h, l) | |
# p: classification score / probability | |
# x,y,z: location | |
# w,h,l: dimensions |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#Sidharth Rajaram, 2017, part of NBA-Predict | |
from sklearn import svm | |
import numpy as np | |
def combineData(values1, values2): | |
combined_stats = [] | |
for a in range(values1.size): | |
result_component = [values1[a],values2[a]] | |
combined_stats.append(result_component) | |
combined_stats = np.array(combined_stats) |