1.报错: TypeError: not all arguments converted during string formatting
代码如下:
string = ''
# 读取数据集的图片
iml = cv2.imread('./yolo/zuo/%szuo%d.bmp' %(string,i) ) # 左图
imr = cv2.imread('./yolo/you/%syou%d.bmp' %(string,i) ) # 右图
2.报错: WARNING conda.gateways.disk.delete:unlink_or_rename_to_trash(140)
WARNING conda.gateways.disk.delete:unlink_or_rename_to_trash(140): Could not remove or rename D:\anaconda\pkgs\pytorch-1.6.0-py3.7_cuda101_cudnn7_0\Lib\site-packages\torch\lib\torch_cuda.dll. Please remove this file manually (you may need to reboot to free file handles)
手动把这个文件夹的 torch_cuda.dll 这个文件删除即可
3.报错： google-auth＜2,＞=1.6.3 not found and is required by YOLOv5
卸载重装即可
4.报错： AttributeError: Cant get attribute SPPF on module models.common
在 model/ common.py这个文件里添加以下代码
import warnings
class SPPF(nn.Module):
# Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
def __init__(self, c1, c2, k=5): # equivalent to SPP(k=(5, 9, 13))
super().__init__()
c_ = c1 // 2 # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c_ * 4, c2, 1, 1)
self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
def forward(self, x):
x = self.cv1(x)
with warnings.catch_warnings():
warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning
y1 = self.m(x)
y2 = self.m(y1)
return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))
使用coco数据集就没问题了，如果使用自己训练的权重文件，会报下方第5个例子的错
这是因为加入了sppf模块之后，前后传输的张量发生了变化
解决方法：找到yolo.py文件，把
@staticmethod
def _make_grid(nx=20, ny=20):
yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
替换成
def _make_grid(self, nx=20, ny=20, i=0):
d = self.anchors[i].device
#if check_version(torch.__version__, '1.10.0'):
if (torch.__version__ >= '0.9.1'):
yv, xv = torch.meshgrid([torch.arange(ny, device=d), torch.arange(nx, device=d)])
else:
yv, xv = torch.meshgrid([torch.arange(ny, device=d), torch.arange(nx, device=d)])
grid = torch.stack((xv, yv), 2).expand((1, self.na, ny, nx, 2)).float()
anchor_grid = (self.anchors[i].clone() * self.stride[i]) \
.view((1, self.na, 1, 1, 2)).expand((1, self.na, ny, nx, 2)).float()
return grid, anchor_grid
大家看我注释的这句话
if check_version(torch.__version__, '1.10.0'):
我是torchvision版本低，用check_version会报错，所以改成了我自己的torchvision版本
if (torch.__version__ >= '0.9.1'):
5.报错： RuntimeError: The size of tensor a (80) must match the size of tensor b (56) at non-singleton
这是由于用了版本5.1，需要替换成6.1的，下载V6.1的版本点击下载
下载好之后替换原来的yolov5s
6.报错： TypeError: meshgrid() got an unexpected keyword argument ‘indexing‘
把报错部分的 indexing=‘ij’ 删除即可
7.报错：AttributeError:‘tuple’ object has no attribute ‘to’
报错代码:
if self.grid[i].shape[2:4] != x[i].shape[2:4]:
self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
修改为:
if self.grid[i].shape[2:4] != x[i].shape[2:4]:
self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
笔记（不用理会）
用yolov5s用下边代码
@staticmethod
def _make_grid(nx=20, ny=20):
yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
if self.grid[i].shape[2:4] != x[i].shape[2:4]:
self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
用自己训练的权重文件将上边分别替换成
def _make_grid(self, nx=20, ny=20, i=0):
d = self.anchors[i].device
#if check_version(torch.__version__, '1.10.0'):
if (torch.__version__ >= '0.9.1'):
yv, xv = torch.meshgrid([torch.arange(ny, device=d), torch.arange(nx, device=d)])
else:
yv, xv = torch.meshgrid([torch.arange(ny, device=d), torch.arange(nx, device=d)])
grid = torch.stack((xv, yv), 2).expand((1, self.na, ny, nx, 2)).float()
anchor_grid = (self.anchors[i].clone() * self.stride[i]) \
.view((1, self.na, 1, 1, 2)).expand((1, self.na, ny, nx, 2)).float()
return grid, anchor_grid
if self.grid[i].shape[2:4] != x[i].shape[2:4]:
self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)