load pretrained pose-net weights

create mimicmotion pipeline and load pretrained weight Args: infer_config (str): device (str or torch.device): "cpu" or "cuda:{d

To calculate the affine matrix, three pairs of points are required. This function is used to get the 3rd point, given 2D points a & b. The 3r

blend color according to point conf

vis dwpose outputs Args: pose (List): DWposeDetector outputs in dwpose_detector.py H (int): height W (int): width

process image pose Args: ref_image (np.ndarray): reference image pixel value Returns: np.ndarray: pose visual image in RGB-m

preprocess ref image pose and video pose Args: video_path (str): video pose path ref_image (np.ndarray): reference image

Appends dimensions to the end of a tensor until it has target_dims dimensions.

Extend the scale to match the given aspect ratio. Args: scale (np.ndarray): The image scale (w, h) in shape (2, ) aspect_ratio (f

Initialize weights with He. initialization and zero out the biases

Rotate a point by an angle. Args: pt (np.ndarray): 2D point coordinates (x, y) in shape (2, ) angle_rad (float): rotation angle i

Transform the bbox format from (x,y,w,h) into (center, scale) Args: bbox (ndarray): Bounding box(es) in shape (4,) or (n, 4), formatted

Modulate simcc distribution with Gaussian. Args: simcc_x (np.ndarray[K, Wx]): model predicted simcc in x. simcc_y (np.ndarray[K,

Get maximum response location and value from simcc representations. Note: instance number: N num_keypoints: K heatmap hei

Calculate the affine transformation matrix that can warp the bbox area in the input image to the output size. Args: center (np.ndarra

Inference RTMPose model. Args: sess (ort.InferenceSession): ONNXRuntime session. img (np.ndarray): Input image in shape. Ret

run human detect

run pose detect Args: session (ort.InferenceSession): ONNXRuntime session. out_bbox (np.ndarray): bbox list oriImg (np.n

Multiclass NMS implemented in Numpy. Class-aware version. Args: boxes (np.ndarray): shape=(N,4); N is number of boxes scores (np.

Single class NMS implemented in Numpy. Args: boxes (np.ndarray): shape=(N,4); N is number of boxes scores (np.ndarray): the score

Patch GEGLU with inplace multiplication to save GPU memory.

Postprocess for RTMPose model output. Args: outputs (np.ndarray): Output of RTMPose model. model_input_size (tuple): RTMPose mode

preprocess ref image pose and video pose Args: video_path (str): input video pose path image_path (str): reference image path

Do preprocessing for RTMPose model inference. Args: img (np.ndarray): Input image in shape. input_size (tuple): Input image size

r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor` or o

Get the bbox image as the model input by affine transform. Args: input_size (dict): The input size of the model. bbox_scale (dict

r""" The call function to the pipeline for generation. Args: image (`PIL.Image.Image` or `List[PIL.Image.Image]` or `torc

call to process dwpose-detect Args: oriImg (np.ndarray): detected image

construnct base model components and load pretrained svd model except pose-net Args: base_model_path (str): pretrained svd model p

r""" Returns: `dict` of attention processors: A dictionary containing all attention processors used in the model with

Sets the attention processor to use [feed forward chunking](https://huggingface.co/blog/reformer#2-chunked-feed-forward-layers).

r""" The [`UNetSpatioTemporalConditionModel`] forward method. Args: sample (`torch.FloatTensor`): The noi

The [`TransformerTemporal`] forward method. Args: hidden_states (`torch.LongTensor` of shape `(batch size, num latent pi

Args: hidden_states (`torch.FloatTensor` of shape `(batch size, channel, height, width)`): Input hidden_states.

Run a single prediction on the model

Disables custom attention processors and sets the default attention implementation.

Load the model into memory to make running multiple predictions efficient