linfengca

图片换个横竖方向，检测结果就不一样

5

图片竖向可以检测到目标，旋转调整为横向保存，检测不到目标； 再旋转成竖向，又可以检测到目标。奇也怪哉，应该修改什么训练参数？

Test 4 clients, each 100 threads, transmission 10000 files，finally, more than ten files were lost. Add trace log for each connect, found that: in multithreading and high concurrency environment, the...

请教大神， 这个报错怎么解决呢？ File "D:\Users\lfchen\anaconda3\lib\site-packages\numba\core\compiler.py", line 395, in _compile_core raise e File "D:\Users\lfchen\anaconda3\lib\site-packages\numba\core\compiler.py", line 386, in _compile_core pm.run(self.state) File "D:\Users\lfchen\anaconda3\lib\site-packages\numba\core\compiler_machinery.py", line 339, in run raise patched_exception File "D:\Users\lfchen\anaconda3\lib\site-packages\numba\core\compiler_machinery.py", line 330, in...

yolov8 官方导出ncnn seg模型使用异常

7

ex.input("in0", in_pad); ncnn::Mat out; ex.extract("out0", out); ncnn::Mat mask_proto; ex.extract("out1", mask_proto); 输入的图片大小in_pad之后w是640，h是512， out0取出的w是8400，h是37，导致后面generate_proposals中const float* scores = pred.row(i) + 4 * reg_max_1; 取值越界， mask_proto取出的貌似没有问题，是w160,h280 请教一下是什么原因？