experimenting.agents package

Agents module

Agents package provides a toolbox agents for a multitude of tasks

Tasks provided

  • Autoencoder

  • Classification

  • Heatmap

  • 2D joint estimation

  • 3D joint estimation

Submodules

experimenting.agents.base module

Base class for agents classes. Each agent provides a dataset factory class to get train, val, and test datasets. Each agent must implement training, validation, and test steps methods as well as epoch_end methods

class experimenting.agents.base.BaseModule(optimizer, lr_scheduler, loss, dataset_constructor, use_lr_scheduler)

experimenting.agents.margipose_estimator module

class experimenting.agents.margipose_estimator.MargiposeEstimator(optimizer: dict, lr_scheduler: dict, loss: dict, core: experimenting.dataset.core.base.BaseCore, model_zoo: str, backbone: str, model: str, stages: int = 3, pretrained: bool = False, use_lr_scheduler=False, estimate_depth=False, test_metrics=None, *args, **kwargs)

Agents for training and testing multi-stage 3d joints estimator using marginal heatmaps (denoted as Margipose)

denormalize_predictions(normalized_predictions, b_y)

Denormalize skeleton prediction and reproject onto original coord system

Parameters

  • normalized_predictions (torch.Tensor) – normalized predictions

  • b_y – batch y object (as returned by 3d joints dataset)

Returns

Returns torch tensor of shape (BATCH_SIZE, NUM_JOINTS, 3)

Note

Prediction skeletons are normalized according to batch depth value z_ref or torso length

forward(x)

For inference. Return normalized skeletons

experimenting.agents.margipose_estimator.predict3d(xy_hm, zy_hm, xz_hm)

Predict normalized 3d skeleton joints

Parameters

outs (list, list, list) – output of the model

Returns

torch tensor of normalized skeleton joints with shape (BATCH_SIZE, NUM_JOINTS, 3)

Note

prediction used dsnnt toolbox