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
你好哦!我想问一下r_net的neg、pos、part的数据集只是用p_net进行hard_example处理嘛?需不需要还对原始的wideface数据集进行处理?
在其它博客看到如下的描述: 由原始图片和PNet生成预测的bounding boxes; 输入原始图片和PNet生成的bounding box,通过RNet,生成校正后的bounding box; 输入元素图片和RNet生成的bounding box,通过ONet,生成校正后的bounding box和人脸面部轮廓关键点。
The text was updated successfully, but these errors were encountered:
Hi @mmcgg 网络的pipline是pnet的输出到rnet的,直接把pnet的输出和原始数据一同作为rnet的输出会不会对rnet的数据分布有影响呢?个人愚见
Sorry, something went wrong.
应该会影响数据分布的,之前的另外一个mtcnn程序中直接用原始数据生成p_net、r_net、o_net的数据,效果不是很好
No branches or pull requests
你好哦!我想问一下r_net的neg、pos、part的数据集只是用p_net进行hard_example处理嘛?需不需要还对原始的wideface数据集进行处理?
在其它博客看到如下的描述:
由原始图片和PNet生成预测的bounding boxes;
输入原始图片和PNet生成的bounding box,通过RNet,生成校正后的bounding box;
输入元素图片和RNet生成的bounding box,通过ONet,生成校正后的bounding box和人脸面部轮廓关键点。
The text was updated successfully, but these errors were encountered: