环境:
模型转换:rknntoolkit2-1.5.0
板端运行:rknntoolkit2-lite
rk3588
偷个图,类似于这个。
用官网yolov5训练的做积水检测(二分类),由于rk推理需要的模型是三输出模型,后处理另外做。官方的模型导出是一输出模型,所以需要在导出前修改models/yolo.py文件:
def forward(self, x):
z = [] # inference output
for i in range(self.nl):
if os.getenv('RKNN_model_hack', '0') != '0':
x[i] = torch.sigmoid(self.m[i](x[i])) # conv
return x
# def forward(self, x):
# z = [] # inference output
# for i in range(self.nl):
# x[i] = self.m[i](x[i]) # conv
# bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)
# x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
#
# if not self.training: # inference
# if self.grid[i].shape[2:4] != x[i].shape[2:4] or self.onnx_dynamic:
# self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
#
# y = x[i].sigmoid()
# if self.inplace:
# y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
# y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
# else: # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
# xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
# wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i].view(1, self.na, 1, 1, 2) # wh
# y = torch.cat((xy, wh, y[..., 4:]), -1)
# z.append(y.view(bs, -1, self.no))
#
# return x if self.training else (torch.cat(z, 1), x)
在修改完这个后有概率会出现花屏,对,有概率。我推理了两个模型,有一个出现了花屏,有一个没有。
解决方案:修改process函数,去掉sigmoid处理,如下图所示。
感谢这位大哥的经验:
【已解决】pt文件转onnx后再转rknn时得到推理图片出现大量锚框变花屏