Zheng Li

RetinaFace mnet.25模型的问题

12

你好，我用你的方法把RetinaFace mnet.25模型转换为onnx格式，然后载入TensorRT,但parseFromFile()调用失败了，TRT库有报告如下的信息: TensorRT_WARNING: onnx2trt_utils.cpp:220: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32. TensorRT_ERROR: builtin_op_importers.cpp:2593 In function...

Supportted YOLOv5 4.0

7

Does support YOLOv5 4.0?

为什么我看别人的代码是160x160，你为什么定义为200x200

Problem about running onnx model on TensorRT lib

2

Hi: I try to running the onnx model on NVIDIA TensorRT lib, firstly I load the version-RFB-320.onnx model, trt lib report below warnings,and detect result is wrong onnx2trt_utils.cpp:220: Your ONNX...

What's the difference between them? why cv dnn module must use version-RFB-320_without_postprocessing.onnx? what's the meaning of "without_postprocessing"?

Hi: I download a pretrained DeepLabV3+ model using PASCAL VOC dataset,I found the network input and output size is only 512x512, this size is a little small,so if I want...

询问下ArcFace的代码，谢谢

1

你好，请问Arcface::normalize()函数是做什么用的？为什么要对输出的特征值做这步处理？ArcFace官方的python代码好像没这步处理？ 还有ArcFace的特征输出长度为512，你这为什么是128？

Hi: Can I use owt-client-native to push encoded video & audio streams(h264+aac) to a WebRTC Server(e.g. kurento-media-server,owt-server,mediasoup) ? Is there any examples ?

用ffmpeg无法进行rtsp推流

8

我输入如下命令进行rtsp推流: ffmpeg -re -i n:/test.mp4 -vcodec copy -acodec copy -f rtsp rtsp://192.168.1.109:554/live.sdp 运行后ffmpeg报错,推流无法进行,错误信息如下: Could not write header for output file #0 (incorrect codec parameters ?): Invalid data found when processing...

请问yangwebrtc能否只做推流

2

就是不做音频和视频的编码，就完成将已编码的音频和视频数据做WEBRTC推流，这样是否可以?