easycv.models.pose.heads package

Submodules

easycv.models.pose.heads.topdown_heatmap_base_head module

easycv.models.pose.heads.topdown_heatmap_base_head.decode_heatmap(heatmaps, img_metas, test_cfg)

class easycv.models.pose.heads.topdown_heatmap_base_head.TopdownHeatmapBaseHead

Bases: torch.nn.modules.module.Module

Base class for top-down heatmap heads.

All top-down heatmap heads should subclass it. All subclass should overwrite:

Methods:get_loss, supporting to calculate loss. Methods:get_accuracy, supporting to calculate accuracy. Methods:forward, supporting to forward model. Methods:inference_model, supporting to inference model.

abstract get_loss(**kwargs)

Gets the loss.

abstract get_accuracy(**kwargs)

Gets the accuracy.

abstract forward(**kwargs)

Forward function.

abstract inference_model(**kwargs)

Inference function.

decode(img_metas, output, **kwargs)

Decode keypoints from heatmaps.

Parameters

• img_metas (list(dict)) – Information about data augmentation By default this includes: - “image_file: path to the image file - “center”: center of the bbox - “scale”: scale of the bbox - “rotation”: rotation of the bbox - “bbox_score”: score of bbox

• output (np.ndarray[N, K, H, W]) – model predicted heatmaps.

training: bool

easycv.models.pose.heads.topdown_heatmap_simple_head module

class easycv.models.pose.heads.topdown_heatmap_simple_head.TopdownHeatmapSimpleHead(in_channels, out_channels, num_deconv_layers=3, num_deconv_filters=(256, 256, 256), num_deconv_kernels=(4, 4, 4), extra=None, in_index=0, input_transform=None, align_corners=False, loss_keypoint=None, train_cfg=None, test_cfg=None)

Bases: easycv.models.pose.heads.topdown_heatmap_base_head.TopdownHeatmapBaseHead

Top-down heatmap simple head. paper ref: Bin Xiao et al. Simple Baselines for Human Pose Estimation and Tracking.

TopdownHeatmapSimpleHead is consisted of (>=0) number of deconv layers and a simple conv2d layer.

Parameters

• in_channels (int) – Number of input channels

• out_channels (int) – Number of output channels

• num_deconv_layers (int) – Number of deconv layers. num_deconv_layers should >= 0. Note that 0 means no deconv layers.

• num_deconv_filters (list|tuple) – Number of filters. If num_deconv_layers > 0, the length of

• num_deconv_kernels (list|tuple) – Kernel sizes.

• in_index (int|Sequence[int]) – Input feature index. Default: 0

• input_transform (str|None) –

  Transformation type of input features. Options: ‘resize_concat’, ‘multiple_select’, None. Default: None.

  • ’resize_concat’: Multiple feature maps will be resized to the

    same size as the first one and then concat together. Usually used in FCN head of HRNet.

  • ’multiple_select’: Multiple feature maps will be bundle into

    a list and passed into decode head.

  • None: Only one select feature map is allowed.

• align_corners (bool) – align_corners argument of F.interpolate. Default: False.

• loss_keypoint (dict) – Config for keypoint loss. Default: None.

__init__(in_channels, out_channels, num_deconv_layers=3, num_deconv_filters=(256, 256, 256), num_deconv_kernels=(4, 4, 4), extra=None, in_index=0, input_transform=None, align_corners=False, loss_keypoint=None, train_cfg=None, test_cfg=None)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

get_loss(output, target, target_weight)

Calculate top-down keypoint loss.

Note

batch_size: N num_keypoints: K heatmaps height: H heatmaps weight: W

Parameters

• output (torch.Tensor[NxKxHxW]) – Output heatmaps.

• target (torch.Tensor[NxKxHxW]) – Target heatmaps.

• target_weight (torch.Tensor[NxKx1]) – Weights across different joint types.

get_accuracy(output, target, target_weight)

Calculate accuracy for top-down keypoint loss.

Note

batch_size: N num_keypoints: K heatmaps height: H heatmaps weight: W

Parameters

• output (torch.Tensor[NxKxHxW]) – Output heatmaps.

• target (torch.Tensor[NxKxHxW]) – Target heatmaps.

• target_weight (torch.Tensor[NxKx1]) – Weights across different joint types.

forward(x)

Forward function.

inference_model(x, flip_pairs=None)

Inference function.

Returns

Output heatmaps.

Return type

output_heatmap (np.ndarray)

Parameters

• x (torch.Tensor[NxKxHxW]) – Input features.

• flip_pairs (None | list[tuple()) – Pairs of keypoints which are mirrored.

training: bool

init_weights()

Initialize model weights.