We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
我在YOLOv5中采用Pconv(输入通道是c)+conv1x1(输入通道c,输出通道2c)组合的方式替换conv3x3(输入通道是c、输出通道是2c),特征图尺度是没有改变的,测试后精度和速度均降低了;我想请问是需要采用Fasternet Block进行来替换conv3x3嘛?它的输入通道、输出通道该怎么设置呢?是否能够提升检测速度?
The text was updated successfully, but these errors were encountered:
你的效果怎么样?从实验结果来看,在表1中,作者比较了相同输入相同输出时使用不同卷积核的推理速度,但是没有比较这时候的精度;在表3中,作者比较了相近参数相近浮点运算数时的推理速度和准确率,由于作者使用的是PConv和1x1卷积,所以相同参数下输出的通道数应该是比较大的。因此,或许,当输入输出通道数一样时效果可能不好,需要扩大输入输出通道数。
Sorry, something went wrong.
要多多实验,这个东西不是口头能说出来的,部分卷积只能说作为一个降低复杂度的思路,具体还得实验
您有做了尝试吗,效果提升了吗。我这里有点报错问题
me too
No branches or pull requests
我在YOLOv5中采用Pconv(输入通道是c)+conv1x1(输入通道c,输出通道2c)组合的方式替换conv3x3(输入通道是c、输出通道是2c),特征图尺度是没有改变的,测试后精度和速度均降低了;我想请问是需要采用Fasternet Block进行来替换conv3x3嘛?它的输入通道、输出通道该怎么设置呢?是否能够提升检测速度?
The text was updated successfully, but these errors were encountered: