Soft NMS改进的非极大值抑制方法的pytorch cuda版本，可以用

话不多说，直接上代码，代码是根据soft max论文提供的代码，修改的，原来的代码是cpu版本，且返回的keep参数并不是原来bbox的序列参数，所以做了部分修改，本人亲测pytorch版本的maskrcnn可用，提高了我的部分结果。

def mine_soft_nms(boxes, sigma = 0.05, Nt = 0.3, threshold = 0.001, method = 2):
	“ori list is an order to log the bbox order!”
	N = boxes.shape[0]
    ori_list = list(np.arange(N))
    for i in range(N):
        maxscore = boxes[i, 4]
        maxpos = i

        tx1 = boxes[i, 0]
        ty1 = boxes[i, 1]
        tx2 = boxes[i, 2]
        ty2 = boxes[i, 3]
        ts = boxes[i, 4]

        pos = i + 1
        # get max box
        while pos < N:
            if maxscore < boxes[pos, 4]:
                maxscore = boxes[pos, 4]
                maxpos = pos
            pos = pos + 1

        # add max box as a detection
        boxes[i, 0] = boxes[maxpos, 0]
        boxes[i, 1] = boxes[maxpos, 1]
        boxes[i, 2] = boxes[maxpos, 2]
        boxes[i, 3] = boxes[maxpos, 3]
        boxes[i, 4] = boxes[maxpos, 4]

        # swap ith box with position of max box
        boxes[maxpos, 0] = tx1
        boxes[maxpos, 1] = ty1
        boxes[maxpos, 2] = tx2
        boxes[maxpos, 3] = ty2
        boxes[maxpos, 4] = ts

        tx1 = boxes[i, 0]
        ty1 = boxes[i, 1]
        tx2 = boxes[i, 2]
        ty2 = boxes[i, 3]
        ts = boxes[i, 4]

        ori_list[i], ori_list[maxpos] = ori_list[maxpos], ori_list[i]

        pos = i + 1
        # NMS iterations, note that N changes if detection boxes fall below threshold
        while pos < N:
            x1 = boxes[pos, 0]
            y1 = boxes[pos, 1]
            x2 = boxes[pos, 2]
            y2 = boxes[pos, 3]
            s = boxes[pos, 4]

            area = (x2 - x1 + 1) * (y2 - y1 + 1)
            iw = (min(tx2, x2) - max(tx1, x1) + 1)
            if iw > 0:
                ih = (min(ty2, y2) - max(ty1, y1) + 1)
                if ih > 0:
                    ua = float((tx2 - tx1 + 1) * (ty2 - ty1 + 1) + area - iw * ih)
                    ov = iw * ih / ua  # iou between max box and detection box

                    if method == 1:  # linear
                        if ov > Nt:
                            weight = 1 - ov
                        else:
                            weight = 1
                    elif method == 2:  # gaussian
                        weight = torch.exp(-(ov * ov) / sigma)
                    else:  # original NMS
                        if ov > Nt:
                            weight = 0
                        else:
                            weight = 1

                    boxes[pos, 4] = weight * boxes[pos, 4]

                    # if box score falls below threshold, discard the box by swapping with last box
                    # update N
                    if boxes[pos, 4] < threshold:
                        boxes[pos, 0] = boxes[N - 1, 0]
                        boxes[pos, 1] = boxes[N - 1, 1]
                        boxes[pos, 2] = boxes[N - 1, 2]
                        boxes[pos, 3] = boxes[N - 1, 3]
                        boxes[pos, 4] = boxes[N - 1, 4]
                        ori_list[pos], ori_list[N - 1] = ori_list[N - 1], ori_list[pos]
                        N = N - 1
                        pos = pos - 1

            pos = pos + 1

    keep = [i for i in range(N)]
    mine_keep = ori_list[:N]
    print("soft nms N: ", N)
    # return torch.Tensor(np.array(mine_keep))
    return torch.LongTensor(mine_keep).cuda()

输入的参数都能看懂，和你的原来的NMS代码的输入输出对其就可以了！