-[Deployment for Bottom-Up models](#deployment-for-bottom-up-models)
-[Joint Inference with Multi-Object Tracking Model FairMOT](#joint-inference-with-multi-object-tracking-model-fairmot)
-[Complete Deploy Instruction and Demo](#4Complete-Deploy-Instruction-and-Demo)
-[Train with custom data](#Train-with-custom-data)
-[BenchMark](#benchmark)
## Introduction
...
...
@@ -29,6 +31,7 @@ The keypoint detection part in PaddleDetection follows the state-of-the-art algo
Top-Down detects the object first and then detect the specific keypoint. The accuracy of Top-Down models will be higher, but the time required will increase by the number of objects.
Differently, Bottom-Up detects the point first and then group or connect those points to form several instances of human pose. The speed of Bottom-Up is fixed and will not increase by the number of objects, but the accuracy will be lower.
At the same time, PaddleDetection provides [PP-TinyPose](./tiny_pose/README_en.md) specially for mobile devices.
...
...
@@ -43,6 +46,7 @@ At the same time, PaddleDetection provides [PP-TinyPose](./tiny_pose/README_en.m
| Detection Model | Keypoint Model | Input Size | Accuracy of COCO | Average Inference Time (FP16) | Params (M) | Flops (G) | Model Weight | Paddle-Lite Inference Model（FP16) |
