YoloV5的源码:
本博客使用的是branch版本,也可以使用tag5.0的版本。
首先在命令行进行下载,
wget https://github.com/ultralytics/yolov5/archive/refs/heads/master.zip
再进行解压,
unzip mater.zip
删除master压缩文件
rm mater.zip
进入到文件夹里面去
code yolov5-master/
激活环境,这里需要python版本>3.6的
conda activate torch1.8
执行export.py文件,导出ONNX,
python export.py
我们只需要输出ONNX,所以只需指定ONNX即可,
python export.py --include=onnx
int代替shape、size的返回值,这里使用了map函数,避免ONNX导出生成gather、shape等节点,
def forward(self, x):
z = []
for i in range(self.nl):
x[i] = self.m[i](x[i])
bs, _, ny, nx = map(int, x[i].shape)
请看代码的最后两句,batch维度指定为-1,
def forward(self, x):
z = []
for i in range(self.nl):
x[i] = self.m[i](x[i])
bs, _, ny, nx = map(int, x[i].shape)
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
if not self.training:
if self.onnx_dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
y = x[i].sigmoid()
if self.inplace:
y[..., 0:2] = (y[..., 0:2] * 2 + self.grid[i]) * self.stride[i]
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]
else:
xy, wh, conf = y.split((2, 2, self.nc + 1), 4)
xy = (xy * 2 + self.grid[i]) * self.stride[i]
wh = (wh * 2) ** 2 * self.anchor_grid[i]
y = torch.cat((xy, wh, conf), 4)
z.append(y.view(-1, int(y.size(1) * y.size(2) * y.size(3), self.no)))
Original: https://blog.csdn.net/qq_23022733/article/details/125606949
Author: 全息数据
Title: YoloV5 的部署【详解】
原创文章受到原创版权保护。转载请注明出处:https://www.johngo689.com/681201/
转载文章受原作者版权保护。转载请注明原作者出处!