search

ZQPei / deep_sort_pytorch

MOT using deepsort and yolov3 with pytorch
MIT License
2.82k stars 726 forks source link

feature extractor batch vs single inference results #53

Open SungjunKim1 opened 5 years ago

SungjunKim1 commented 5 years ago

in my test case,

image1, image2

im_crops = [image1, image2] features = feature_extractor(im_crops) feature1 = features[0] feature2 = features[1]

feature3 = feature_extractor([image1])[0] feature4 = feature_extractor([image2])[0]

feature1 and feature3 are different.

is my test wrong ? or am i using extractor incorrectly? i think feature1 and feature3 are must be same .. because of 'batch inference'

SungjunKim1 commented 5 years ago

need to eval()