Z-Jeff

> 因为模型的输入是160*160的图像，要把最开始的的图像大小改为 image_size = 160，这样就不报错了。 我也遇到同样的问题，用楼上的方法解决了

Thanks, It really works!

> example I have removed ` -march=native ` in g2o and ORB_SLAM3, and rebuild. But Segmentation fault still occurs. I figure out `SaveAtlas()` result in this error, but I have...

> Try using the usb3.0 It really works for me!

我也遇到了这个问题。 我的电脑系统是Ubuntu20.04，非虚拟机。 尝试加上： find_package(Boost REQUIRED) find_package(Boost COMPONENTS filesystem thread REQUIRED) 也没解决这个问题。 请问有其他解决办法吗？

> 我搞清楚了，是在“MYNT-EYE-S-SDK/wrappers/ros/src/mynt_eye_ros_wrapper/CMakeLists.txt”中添加这两行： find_package(Boost REQUIRED) find_package(Boost COMPONENTS filesystem thread REQUIRED) 问题就解决了。 之前修改的是“MYNT-EYE-S-SDK/CMakeLists.txt”，无法解决问题。

There is a bug in "mtcnn/data_preprocess/gen_Pnet_train_data.py". 'boxes' should be the form of [x1, y1, x2, y2], while the data in "./anno_store/anno_train.txt" is [x1, x2, dx, dy]. So, correct the form...

What's more, there is a same question in "gen_Rnet_train_data.py" and "gen_Onet_train_data.py". Deal it in the same way.

I have meet the same problem. P-Net and R-Net work well, but O-Net doesn't detect any faces or landmarks. Have you solve this problem?

I have solve this problem just now. 'boxes' should be the form of [x1, y1, x2, y2], while the data in "./anno_store/anno_train.txt" is [x1, x2, dx, dy]. I have changed...