jwyang/faster-rcnn.pytorch

NMS_GPU different results from NMS_CPU

Open

#220 aberto em 29 de jun. de 2018

Ver no GitHub
 (19 comments) (0 reactions) (0 assignees)Python (2.342 forks)batch import
help wanted

Métricas do repositório

Stars
 (7.454 stars)
Métricas de merge de PR
 (Nenhuma PRs mesclada em 30d)

Description

I compiled successfully in Ubuntu 14.04 and I use Python 3.6

import numpy as np
detections = torch.from_numpy(np.array([
    (12, 84, 140, 212, 0.1),
	(24, 84, 152, 212, 0.8),
	(36, 84, 164, 212, 0.7),
	(12, 96, 140, 224, 0.6),
	(24, 96, 152, 224, 0.5),
	(24, 108, 152, 236, 0.9)
]))

# print(detections)
print(nms_gpu(detections, 0.1))
print(nms_cpu(detections, 0.1))

## print results below
tensor([], dtype=torch.int32)
tensor([ 5], dtype=torch.int32)

You can see here, the CPU results is correct, whereas the GPU results is not returning anything

Guia do colaborador