lazylazypig
lazylazypig
@Hyperjunct 你这个错误看起来是某一帧没有检测到目标，程序内部没有做好防护导致的；我也遇到了相同的问题，暂时还没有解决
@wjq842121846 @Hyperjunct 修改文件PaddleDetection\deploy\pptracking\python\mot_sde_infer.py中的SDE_Detector.reidprocess(...)函数，大约254行，改为： ``` if len(keep_idx[0]) == 0: # det_results['boxes'] = np.zeros((1, 6), dtype=np.float32) # det_results['embeddings'] = None det_results['boxes'] = np.zeros((0, 6), dtype=np.float32) #返回一个空的数组 det_results['embeddings'] = np.full((0, 0), None) #返回一个空的数组...
@gangm hi, sorry for my late reply. it's been a long while since i tested dlib on tk1, so i cannot remember the exact time cost for detecting one picture....
@bth5032 Hi, have you sloved the 'import caffe' problem?
@pawan9 hi, could you share your rtsp reconnection logic implementation? when the stream stop (maybe caused by the bad network)， an "eos" message is sent to the source pipeline's bus,...
@mgerhardy excuse me, what's the final solution?
请问有什么进展吗？我也遇到类似的问题~_~
@mengxizeng rknn-toolkit 1.7.3您用过么？改为opset=10后，倒是不报slice算子的错误了，出了split的错误： Can not find rknn layer for Tensor [Split_Split_225:out1]. rknn这玩意感觉就是个半成品，问个啥问题官方屁都不放一个
@kywish hi; any updates or you have solve the ploblem?
@013292 您好，请问找到原因了吗？