类型错误：列表索引必须为整数或切片，而不是cupy.core.core.ndarray。

Question

类型错误：列表索引必须为整数或切片，而不是cupy.core.core.ndarray。

python-3.xgpuobject-detectionnmscupy

3

在目标检测算法中，使用非极大值抑制（NMS）来丢弃物体（例如车辆）的多余检测结果。

通常，水平边界框用于目标检测算法，并且已经存在水平NMS的GPU实现，但是我想要拥有旋转边界框的GPU实现。

CPU实现已经完成，但我正在努力使用CuPy包将CPU版本转换为GPU版本。下面是我编写的代码。在代码部分之后，您可以看到错误信息。

我的问题是什么原因导致了TypeError：list indices must be integers or slices, not cupy.core.core.ndarray？

    from shapely.geometry import Polygon as shpoly
    import time
    
    #### CPU implementation
    import numpy as np   
    
    def polygon_iou(poly1, poly2):
      """
      Intersection over union between two shapely polygons.
      """
      if not poly1.intersects(poly2): # this test is fast and can accelerate calculation
        iou = 0
      else:
        try:
          inter_area = poly1.intersection(poly2).area
          union_area = poly1.area + poly2.area - inter_area
          iou = float(inter_area) / float(union_area)
        except shapely.geos.TopologicalError:
          warnings.warn("'shapely.geos.TopologicalError occured, iou set to 0'", UserWarning)
          iou = 0
        except ZeroDivisionError:
          iou = 0
      return iou
    
    def polygon_from_array(poly_):
      """
      Create a shapely polygon object from gt or dt line.
      """
      polygon_points = np.array(poly_).reshape(4, 2)
      polygon = shpoly(polygon_points).convex_hull
      return polygon
    
    def nms(dets, thresh):
        scores = dets[:, 8]
        order = scores.argsort()[::-1]
        polys = []
        areas = []
        for i in range(len(dets)):
            tm_polygon = polygon_from_array(dets[i,:8])
            polys.append(tm_polygon)
        keep = []
        while order.size > 0:
            ovr = []
            i = order[0]
            keep.append(i)
            for j in range(order.size - 1):
                iou = polygon_iou(polys[i], polys[order[j + 1]])
                ovr.append(iou)
            ovr = np.array(ovr)
            inds = np.where(ovr <= thresh)[0]
            order = order[inds + 1]
        return keep
    
    
    #### GPU implementation
    import cupy as cp  
      
    def polygon_iou_gpu(poly1, poly2):
      """
      Intersection over union between two shapely polygons.
      """
      if not poly1.intersects(poly2): # this test is fast and can accelerate calculation
        iou = 0
      else:
        try:
          inter_area = poly1.intersection(poly2).area
          union_area = poly1.area + poly2.area - inter_area
          iou = float(inter_area) / float(union_area)
        except shapely.geos.TopologicalError:
          warnings.warn("'shapely.geos.TopologicalError occured, iou set to 0'", UserWarning)
          iou = 0
        except ZeroDivisionError:
          iou = 0
      return iou
    
    def polygon_from_array_gpu(poly_):
      """
      Create a shapely polygon object from gt or dt line.
      """
      polygon_points = cp.array(poly_).reshape(4, 2)
      polygon = shpoly(polygon_points).convex_hull
      return polygon
    
    def nms_gpu(dets, thresh):
        scores = dets[:, 8]
        order = scores.argsort()[::-1]
        polys = []
        areas = []
        for i in range(len(dets)):
            tm_polygon = polygon_from_array_gpu(dets[i,:8])
            polys.append(tm_polygon)
        keep = []
        while order.size > 0:
            ovr = []
            i = order[0]
            keep.append(i)
            for j in range(order.size - 1):   
                iou = polygon_iou_gpu(polys[i], polys[order[j + 1]])
                ovr.append(iou)
            ovr = np.array(ovr)
            inds = np.where(ovr <= thresh)[0]
            order = order[inds + 1]
        return keep
    
    
    if __name__ == '__main__':
        import random
        boxes = np.random.randint(0,100,(1000,8))
        scores = np.random.rand(1000, 1)
        dets = np.hstack((boxes, scores[:])).astype(np.float32)

    
        thresh = 0.1
        start = time.time()
        keep = nms(dets, thresh)
        print("CPU implementation took: {}".format(time.time() - start))
    
        cp.cuda.Device(1)
        dets_gpu = cp.array(dets)
        start = time.time()
        keep = nms_gpu(dets_gpu, thresh)
        print("GPU implementation took: {}".format(time.time() - start))

错误消息为：

CPU implementation took: 0.3672311305999756

Traceback (most recent call last):

File "nms_rotated.py", line 117, in
keep = nms_gpu(dets_gpu, thresh)
File "nms_rotated.py", line 97, in nms_gpu
iou = polygon_iou_gpu(polys[i], polys[order[j + 1]])
TypeError: list indices must be integers or slices, not cupy.core.core.ndarray

更新：2019年2月13日我尝试了@Yuki Hashimoto的答案，将iou = polygon_iou_gpu(polys[i], polys[order[j + 1]])替换为iou = polygon_iou_gpu(polys[i.get()], polys[order[j + 1].get()])。没有出现任何错误，但GPU版本比CPU版本慢多倍。

使用100000个随机检测：

      CPU implementation took: 47.125494956970215
      GPU implementation took: 142.08464860916138

- Majid Azimi

2个回答

0

[更新于2019/2/13]

请参考@yuki-hashimoto的答案，更为合适。

正如错误信息所述

TypeError: 列表索引必须是整数或切片，而不是cupy.core.core.ndarray

我猜测 order 是 cupy 数组？如果是这种情况，那么 polys[order[j + 1]] 使用的索引 order[j+1] 是 cupy 数组，可能会导致问题。尝试使用 cuda.to_cpu(array) 方法将它们转换为 numpy 数组怎么样？

from chainer import cuda
iou = polygon_iou_gpu(polys[i], polys[cuda.to_cpu(order[j + 1])])

- corochann

将其转换为numpy数组实际上是朝着CPU实现的方向发展。目标是通过使用CuPy来加速。 - Majid Azimi

它只向GPU发送索引“order”，这只是很小的一部分。如果你想获得GPU的好处，可以在GPU上计算大数组。我猜上面的示例代码使用了小数组，在这种情况下，我认为简单地在CPU上计算会更快。 - corochann

1

哦，现在我明白你的意思了。我已经修改了代码以考虑随机100个检测。但我仍然有同样的问题。我尝试了@yuki-hashimoto的答案。我也尝试了你的答案。它可以工作，但GPU的速度比CPU慢得多，当有10000个随机检测时。 - Majid Azimi

网页内容由stack overflow 提供, 点击上面的

可以查看英文原文，
原文链接

- Yuki Hashimoto · Accepted Answer

简述：使用PFN官方的非极大值抑制。

详细说明：使用cp.where，它返回与某个条件匹配的list对象。

“corochann”的回答并不推荐，因为“polys”是一个列表，而列表不应该被“np.ndarray”切片（注入另一个依赖项也不推荐...）。

>>> polys[order.get()]  # get method returns np.ndarray
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
TypeError: only integer scalar arrays can be converted to a scalar index
>>> polys[order[j + 1].get()]
### some result in some case, but this may fails depending on your env.###