Skip to content

Latest commit

 

History

History
90 lines (54 loc) · 5.91 KB

File metadata and controls

90 lines (54 loc) · 5.91 KB
graph LR
    Training_Orchestration["Training Orchestration"]
    Epoch_Training_Loops["Epoch Training Loops"]
    Loss_Computation["Loss Computation"]
    Evaluation_Orchestration["Evaluation Orchestration"]
    Core_Evaluation_Metrics["Core Evaluation Metrics"]
    Specialized_Evaluation_Modules["Specialized Evaluation Modules"]
    Training_Orchestration -- "initiates and manages" --> Epoch_Training_Loops
    Epoch_Training_Loops -- "invokes for loss calculation" --> Loss_Computation
    Epoch_Training_Loops -- "periodically invokes for validation" --> Evaluation_Orchestration
    Loss_Computation -- "returns computed loss values to" --> Epoch_Training_Loops
    Evaluation_Orchestration -- "provides validation results back to" --> Epoch_Training_Loops
    Evaluation_Orchestration -- "calls functions within" --> Core_Evaluation_Metrics
    Evaluation_Orchestration -- "delegates tasks to" --> Specialized_Evaluation_Modules
    Core_Evaluation_Metrics -- "returns calculated error values to" --> Evaluation_Orchestration
    Specialized_Evaluation_Modules -- "returns formatted results to" --> Evaluation_Orchestration
Loading

CodeBoardingDemoContact

Details

The Model Training & Evaluation subsystem is crucial for the development and refinement of deep learning models within the ROMP project. It encompasses the entire lifecycle from initiating training runs to comprehensive performance assessment.

Training Orchestration

Manages the overall training process, including model and optimizer initialization, data loading setup, and the high-level coordination of training and validation epochs. It acts as the primary entry point for initiating training runs.

Related Classes/Methods:

Epoch Training Loops

Implements the core iterative logic for a single training epoch. This includes performing forward passes, calculating loss, executing backward passes for gradient computation, and updating model parameters. It also manages calls to validation routines.

Related Classes/Methods:

Loss Computation

Responsible for calculating various loss components (e.g., keypoint, parameter, detection, temporal, camera loss) by comparing model predictions against ground truth data. It aggregates these individual losses into a total loss value used for optimization.

Related Classes/Methods:

Evaluation Orchestration

Serves as the primary entry point for model evaluation. It coordinates the inference process on validation or test datasets, manages the collection of predictions, and orchestrates the calculation and presentation of overall performance metrics.

Related Classes/Methods:

Core Evaluation Metrics

Provides a set of fundamental, reusable functions for computing standard evaluation metrics such as Mean Per Joint Position Error (MPJPE), Procrustes-aligned MPJPE (P-MPJPE), and vertex errors. These functions are designed for broad applicability across different evaluation scenarios.

Related Classes/Methods:

Specialized Evaluation Modules

Adapts the general evaluation framework to the unique characteristics, data formats, and ground truth annotations of specific datasets (e.g., AGORA, Relative Human, CMU Panoptic) and focuses on evaluating multi-person tracking algorithms in video sequences.

Related Classes/Methods: