谢晟 comments

Results 12 comments of


                                            谢晟

Video inference is not satisfactory

You can use yolov5 replace yolov3

Testing realtime demo on ST-GCN project with a mmskeleton trained model

我也是这个问题，需要用openpose来生成数据集吗，那样又回到老版本去了

pretrain models 能否加个百度网盘的分享？fall detection下载不了，有大神帮忙共享下吗

你加我QQ吧，我发你406174050

这个能用在剪枝的模型上吗？

Can you tell me the result for YOLOv3-model-pruning,thank you

miss datasets.dummy_datasets

我从caffe2官网下载了原文件，infer.py应该要修改才能用吧，请问能提供修改版本吗，谢谢

ArcFace model query

@pranavsharma please tell me how to use yolov3(keras-to-onnx),I use it in tensorrt-inference-service get lots nan.

TypeError: Error converting shape to a TensorShape: int() argument must be a string, a bytes-like object or a number, not 'tuple'

我将flag_nms设置为True后，运行时也出现这一问题。 File "demo_video_mobile.py", line 192, in light_track keypoints = inference_keypoints(pose_estimator, bbox_det_dict)[0]["keypoints"] File "demo_video_mobile.py", line 554, in inference_keypoints cls_dets, keep = apply_nms(cls_dets, nms_method, nms_thresh) File "demo_video_mobile.py", line 572, in apply_nms keep...

test acc is :0.0%

我也遇到这一问题，没有任何改变，运行程序没有输出，acc为0。请问作者的环境和版本是多少

谢晟

Built a WeChat group