Dr.He
Dr.He
@ver0z you can pass it float numbers like [0.1 0.6 0.2 0.4]
@kb1ooo have you solved the problem? I guess that the lib versions matter?
@babyblue1334 In Windows, the name of libturbojpeg has the suffix of .dll , not .so in Linux.
@Maping1026 you can search for some solutions.
@zkxwy1996 do you install LFD successfully ? It seems that nms go wrong. You have to make sure that nms is compiled correctly.
@jinfagang You may downsample images by 2x or even 3x. You have to know that the detection range of the detector is controlled by `config_dict['detection_scales'] = ((4, 20), (20, 40),...
@jinfagang I think you do not grasp some basic concepts. [4, 320] (in pixels) is object scale that the detector can detect. Of cause you can set it as your...
@jinfagang Ok, I will try, you just provide the dataset.
@jinfagang You mean this [dataset](http://www.crowdhuman.org/)?
@dexception I am trying to merge LFD into mmdetection. After that, you may enjoy new deployment via mmdeploy.