xia

Support training for 5 yolo layers?

3

The project [https://github.com/AlexeyAB/darknet/blob/master/cfg/yolov3_5l.cfg](url) has supported 5 yolo layers. Does your project support training for 5 yolo layers?

[Training Issue] How to output test loss?

1

Model : yolov3 Questions : I want to output mAP and test loss in test stage, so i set test_compute_loss: True in solver.prototxt. But the Test loss always is 0,...

[Feature Request] Improvment in YOLOv3

1

[https://pdfs.semanticscholar.org/ec96/b6ae95e1ebbe4f7c0252301ede26dfc79467.pdf](https://pdfs.semanticscholar.org/ec96/b6ae95e1ebbe4f7c0252301ede26dfc79467.pdf) This is a paper of CVPR2019, Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors. This paper presents a training technique to improve yolo mAP.

make error

1

### Issue summary Hi,Thanks for your code,but I encountered a problem when "make all": PROTOC src/caffe/proto/caffe.proto CXX .build_release/src/caffe/proto/caffe.pb.cc CXX src/caffe/data_reader.cpp CXX src/caffe/common.cpp src/caffe/common.cpp(140): error: identifier "omp_get_thread_num" is undefined if (0...

floating point exception(core dump)

1

运行yolov7-tiny的时候出现了floating point exception(core dunp)错误。  该错误信息出现在rknn.build的时候，当rknn.config函数中取消target='rk3588'时没有该错误。

void img_resize_fast(rga_context *rga_ctx, int src_fd, int src_w, int src_h, uint64_t dst_phys, int dst_w, int dst_h); void img_resize_slow(rga_context *rga_ctx, void *src_virt, int src_w, int src_h, void *dst_virt, int dst_w, int dst_h,...

I want to change three channel RGB image into single channel Gray image. Can you help me? thank you!