报错日志:
NotImplementedError: Could not run 'torchvision::nms' with arguments from the 'CUDA' backend. This could be because the operator doesn't exist for this backend, or was omitted during the selective/custom build process (if using custom build). If you are a Facebook employee using PyTorch on mobile, please visit https://fburl.com/ptmfixes for possible resolutions. 'torchvision::nms' is only available for these backends: [Dense, Negative, UNKNOWN_TENSOR_TYPE_ID, QuantizedXPU, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, SparseCPU, SparseCUDA, SparseHIP, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, SparseVE, UNKNOWN_TENSOR_TYPE_ID, NestedTensorCUDA, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID, UNKNOWN_TENSOR_TYPE_ID].
CPU: registered at C:\b\abs_88nq4vr9ec\croot\torchvision_1670313558208\work\torchvision\csrc\ops\cpu\nms_kernel.cpp:112 [kernel]
QuantizedCPU: registered at C:\b\abs_88nq4vr9ec\croot\torchvision_1670313558208\work\torchvision\csrc\ops\quantized\cpu\qnms_kernel.cpp:125 [kernel]
BackendSelect: fallthrough registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\core\BackendSelectFallbackKernel.cpp:3 [backend fallback]
Python: registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\core\PythonFallbackKernel.cpp:133 [backend fallback]
Named: registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\core\NamedRegistrations.cpp:7 [backend fallback]
Conjugate: registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\ConjugateFallback.cpp:18 [backend fallback]
Negative: registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\NegateFallback.cpp:18 [backend fallback]
ZeroTensor: registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\ZeroTensorFallback.cpp:86 [backend fallback]
ADInplaceOrView: fallthrough registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\core\VariableFallbackKernel.cpp:64 [backend fallback]
AutogradOther: fallthrough registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\core\VariableFallbackKernel.cpp:35 [backend fallback]
AutogradCPU: fallthrough registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\core\VariableFallbackKernel.cpp:39 [backend fallback]
AutogradCUDA: fallthrough registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\core\VariableFallbackKernel.cpp:47 [backend fallback]
AutogradXLA: fallthrough registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\core\VariableFallbackKernel.cpp:51 [backend fallback]
AutogradMPS: fallthrough registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\core\VariableFallbackKernel.cpp:59 [backend fallback]
AutogradXPU: fallthrough registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\core\VariableFallbackKernel.cpp:43 [backend fallback]
AutogradHPU: fallthrough registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\core\VariableFallbackKernel.cpp:68 [backend fallback]
AutogradLazy: fallthrough registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\core\VariableFallbackKernel.cpp:55 [backend fallback]
Tracer: registered at C:\cb\pytorch_1000000000000\work\torch\csrc\autograd\TraceTypeManual.cpp:295 [backend fallback]
AutocastCPU: fallthrough registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\autocast_mode.cpp:481 [backend fallback]
Autocast: fallthrough registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\autocast_mode.cpp:324 [backend fallback]
Batched: registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\BatchingRegistrations.cpp:1064 [backend fallback]
VmapMode: fallthrough registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\VmapModeRegistrations.cpp:33 [backend fallback]
Functionalize: registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\FunctionalizeFallbackKernel.cpp:89 [backend fallback]
PythonTLSSnapshot: registered at C:\cb\pytorch_1000000000000\work\aten\src\ATen\core\PythonFallbackKernel.cpp:137 [backend fallback]
点进去boxes.py 自己重写实现nms方法加到最上面:
class MyNms:
def box_area(self,boxes: Tensor) -> Tensor:
"""
Computes the area of a set of bounding boxes, which are specified by its
(x1, y1, x2, y2) coordinates.
Arguments:
boxes (Tensor[N, 4]): boxes for which the area will be computed. They
are expected to be in (x1, y1, x2, y2) format
Returns:
area (Tensor[N]): area for each box
"""
return (boxes[:, 2] - boxes[:, 0]) * (boxes[:, 3] - boxes[:, 1])
def box_iou(self,boxes1: Tensor, boxes2: Tensor) -> Tensor:
"""
Return intersection-over-union (Jaccard index) of boxes.
Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
Arguments:
boxes1 (Tensor[N, 4])
boxes2 (Tensor[M, 4])
Returns:
iou (Tensor[N, M]): the NxM matrix containing the pairwise IoU values for every element in boxes1 and boxes2
"""
area1 = box_area(boxes1) # 每个框的面积 (N,)
area2 = box_area(boxes2) # (M,)
lt = torch.max(boxes1[:, None, :2], boxes2[:, :2]) # [N,M,2] # N中一个和M个比较; 所以由N,M 个
rb = torch.min(boxes1[:, None, 2:], boxes2[:, 2:]) # [N,M,2]
wh = (rb - lt).clamp(min=0) # [N,M,2] #小于0的为0 clamp 钳;夹钳;
inter = wh[:, :, 0] * wh[:, :, 1] # [N,M]
iou = inter / (area1[:, None] + area2 - inter)
return iou # NxM, boxes1中每个框和boxes2中每个框的IoU值;
def nms(self,boxes: Tensor, scores: Tensor, iou_threshold: float):
"""
:param boxes: [N, 4], 此处传进来的框,是经过筛选(NMS之前选取过得分TopK)之后, 在传入之前处理好的;
:param scores: [N]
:param iou_threshold: 0.7
:return:
"""
keep = [] # 最终保留的结果, 在boxes中对应的索引;
idxs = scores.argsort() # 值从小到大的 索引
while idxs.numel() > 0: # 循环直到null; numel(): 数组元素个数
# 得分最大框对应的索引, 以及对应的坐标
max_score_index = idxs[-1]
max_score_box = boxes[max_score_index][None, :] # [1, 4]
keep.append(max_score_index)
if idxs.size(0) == 1: # 就剩余一个框了;
break
idxs = idxs[:-1] # 将得分最大框 从索引中删除; 剩余索引对应的框 和 得分最大框 计算IoU;
other_boxes = boxes[idxs] # [?, 4]
ious = box_iou(max_score_box, other_boxes) # 一个框和其余框比较 1XM
idxs = idxs[ious[0] <= iou_threshold]
keep = idxs.new(keep) # Tensor
return keep
然后改一下调用即可: