想知道换了自己训练模型后，如何修改其相应的class和输入输出张量配置？

[LMR2018]

想知道换了自己训练模型后，如何修改其相应的class和输入输出张量配置？

W/ncnn: overwrite existing custom layer type YoloV5Focus D/current use model: picodet-s-416.param W/ncnn: AAssetManager_open picodet-s-416.param failed AAssetManager_open picodet-s-416.bin failed D/ncnn: current use model: picodet-s-416 E/model: current_model I/System.out: 0 1 D/mali_winsys: EGLint new_window_surface(egl_winsys_display *, void *, EGLSurface, EGLConfig, egl_winsys_surface **, egl_color_buffer_format *, EGLBoolean) returns 0x3000 I/[Gralloc]: Got handle 10 for fd 92 leave, w : 198, h : 75, format : 0x1,internal_format : 0x1, usage : 0xb00. size=62400,pixel_stride=208,byte_stride=832 leave: prime_fd=92,share_attr_fd=93 W/libEGL: EGLNativeWindowType 0x762ab67010 disconnect failed W/libEGL: EGLNativeWindowType 0x762ab69010 disconnect failed

[JiweiMaster]

https://github.com/JiweiMaster/PP-PicoDet-Android-Demo/blob/master/app/src/main/jni/nanodet.cpp 修改这个文件的相关部分

[Cuttymon]

请问，相关部分有哪些呢，实在看不懂了

[LMR2018]

https://github.com/JiweiMaster/PP-PicoDet-Android-Demo/blob/master/app/src/main/jni/nanodet.cpp

@1138331845 请问你解决了吗？ 在这里面找了改 https://github.com/JiweiMaster/PP-PicoDet-Android-Demo/blob/master/app/src/main/jni/nanodet.cpp