完整內容請訪問：https://blog.csdn.net/chitiantong/article/details/114937760
文章目錄
本篇文章充當搬運工，賺點下載積分。
1.AutoFlip Saliency-aware Video Cropping
2.Box Tracking
3.Dataset Preparation with MediaSequence
4.Face Detection 人臉檢測
5.Face Mesh 人臉網格
6.Hair Segmentation 頭發分割
7.Hands 手部檢測和跟蹤
8.Holistic 全面跟蹤
9.Instant Motion Tracking 即時運動跟蹤
10.Iris 虹膜
11.KNIFT (Template-based Feature Matching)
12.Object Detection
13.Objectron (3D Object Detection) 三維目標檢測
14.Pose 姿勢跟蹤
本篇文章充當搬運工，賺點下載積分。
1.AutoFlip Saliency-aware Video Cropping
自動翻轉顯著性感知視頻裁剪
AutoFlip is an automatic video cropping pipeline built on top of MediaPipe. This example focuses on demonstrating how to use AutoFlip to convert an input video to arbitrary aspect ratios.
AutoFlip是構建在MediaPipe之上的自動視頻裁剪管道。本示例重點演示如何使用AutoFlip將輸入視頻轉換為任意縱橫比。
2.Box Tracking
下載 objecttrackinggpu.apk
3.Dataset Preparation with MediaSequence
用MediaSequence准備數據集
MediaPipe is a useful and general framework for media processing that can assist with research, development, and deployment of ML models. This example focuses on development by demonstrating how to prepare video data for training a TensorFlow model.
The MediaSequence library provides an extensive set of tools for storing data in TensorFlow.SequenceExamples. SequenceExamples provide matched semantics to most video tasks and are efficient to use with TensorFlow. The sequence semantics allow for a variable number of annotations per frame, which is necessary for tasks like video object detection, but very difficult to encode in TensorFlow.Examples. The goal of MediaSequence is to simplify working with SequenceExamples and to automate common preparation tasks. Much more information is available about the MediaSequence pipeline, including how to use it to process new data sets, in the documentation of MediaSequence.
MediaPipe是一個有用的、通用的媒體處理框架，可以幫助研究、開發和部署ML模型。本例通過演示如何准備用於訓練張量流模型的視頻數據來關注開發。
MediaSequence庫提供了一套廣泛的工具，用於將數據存儲在TensorFlow.Sequence示例. SequenceExamples為大多數視頻任務提供匹配的語義，並且可以有效地與TensorFlow一起使用。序列語義允許每幀具有可變數量的注釋，這對於視頻對象檢測之類的任務是必需的，但是很難在其中進行編碼TensorFlow.示例. MediaSequence的目標是簡化使用SequenceExamples的工作，並自動化常見的准備任務。MediaSequence文檔中提供了有關MediaSequence管道的更多信息，包括如何使用它處理新的數據集。
4.Face Detection 人臉檢測
下載 facedetectiongpu.apk
5.Face Mesh 人臉網格
下載 faceeffect.apk
6.Hair Segmentation 頭發分割
下載 hairsegmentationgpu.apk
7.Hands 手部檢測和跟蹤
下載 handdetectiongpu.apk
8.Holistic 全面跟蹤
下載 holistictrackinggpu.apk
9.Instant Motion Tracking 即時運動跟蹤
下載 instantmotiontracking.apk
10.Iris 虹膜
下載 iristrackinggpu.apk
11.KNIFT (Template-based Feature Matching)
下載 templatematchingcpu.apk
MediaPipe KNIFT is a template-based feature matching solution using KNIFT (Keypoint Neural Invariant Feature Transform).
MediaPipe KNIFT是一種基於模板的特征匹配解決方案，使用KNIFT（Keypoint Neural Invariant feature Transform）。
12.Object Detection
下載 objectdetectiongpu.apk
13.Objectron (3D Object Detection) 三維目標檢測
下載 Objectron (3D Object Detection) 三維目標檢測.zip
14.Pose 姿勢跟蹤
下載 posetrackinggpu.apk
————————————————
版權聲明：本文為CSDN博主「煞比貓」的原創文章，遵循CC 4.0 BY-SA版權協議，轉載請附上原文出處鏈接及本聲明。
原文鏈接：https://blog.csdn.net/chitiantong/article/details/114937760