Support multi-batch inference. Add some useful tools, includinganalyze_logs,get_flops,print_config. Support more backbone networks. ResNest VGG New Features Support UDP (#353,#371,#402) Support multi-batch inference (#390) Support MHP dataset (#386) Support pose tracking demo (#380) Support ...
We summarize the model complexity and inference speed of major models in MMPose, including FLOPs, parameter counts and inference speeds on both CPU and GPU devices with different batch sizes. Please refer to inference_speed_summary.md for more details. Data Preparation Please refer to data_preparat...
ConfigInput SizeAP(COCO)PCK@0.1(Body8)AUC(Body8)Params(M)FLOPS(G)ORT-Latency(ms)(i7-11700)TRT-FP16-Latency(ms)(GTX 1660Ti)ncnn-FP16-Latency(ms)(Snapdragon 865)Download RTMPose-t* 256x192 65.9 91.44 63.18 3.34 0.36 3.20 1.06 9.02 pthonnx RTMPose-s* 256x192 69.7 92.45 65.15 5.47...
ConfigInput SizeAP (COCO)Params(M)FLOPS(G)ORT-Latency(ms) (i7-11700)TRT-FP16-Latency(ms) (GTX 1660Ti)ncnn-FP16-Latency(ms) (Snapdragon 865) RTMPose-l 256x192 76.5 4.16 76.5 27.66 4.16 18.85安装 创建一个 conda 虚拟环境并激活它。