Returns a record from table in constant runtime. :param table_name: Table name. :param token: Token of the record. :r

Load a table and return it. :param table_name: The name of the table to load. :return: The table dictionary.

Load a pretrained model from the Hugging Face hub. Arguments: model_id (str): The Hugging Face repository ID. **

A wrapper around :function:`torch.nn.functional.grid_sample` to support 3D point_coords tensors. Unlike :function:`torch.nn.functional.grid_s

Load tables and add them to self, if not already loaded. :param table_names: The names of the nuImages tables to be loaded.

3x3 convolution with padding

Apply non-overlapping constraints to the object scores in pred_masks. Here we keep only the highest scoring object at each spatial lo

Consolidate the per-object temporary outputs in `temp_output_dict_per_obj` on a frame into a single output for all objects, including

Resize the object scores to the original video resolution (video_res_masks) and apply non-overlapping constraints for final output.

Resize the object scores to the original video resolution (video_res_masks) and apply non-overlapping constraints for final output.

Consolidate the per-object temporary outputs in `temp_output_dict_per_obj` on a frame into a single output for all objects, including

Compute the image features on a given frame.

Get the total number of unique object ids received so far in this session.

Get the total number of unique object ids received so far in this session.

Predict masks for the given input prompts, using the currently set image. Input prompts are batched torch tensors and are expected to

Prepare and flatten visual features.

Initialize the weights in backbone. Args: pretrained (str, optional): Path to pre-trained weights. Defaults t

Decode the mask from base64 string to binary string, then feed it to the external pycocotools library to get a mask. :param mask: The mask di

Expects a torch tensor with length 2 in the last dimension. The coordinates can be in absolute image or normalized coordinates, If th

Split a multi-object output into per-object output slices and add them into `output_dict_per_obj`. The resulting slices share the sam

Return an activation function given a string

Return an activation function given a string

Compute the image features on a given frame.

`maskmem_pos_enc` is the same across frames and objects, so we cache it as a constant in the inference session to reduce session stor

Map client-side object id to model-side object index.

Map client-side object id to model-side object index.

Run tracking on a single frame based on current inputs and previous memory.

Run tracking on a single frame based on current inputs and previous memory.

Get the image feature on the input batch.

Get the connected components (8-connectivity) of binary masks of shape (N, 1, H, W). Inputs: - mask: A binary mask tensor of shape (N, 1

Returns the positional encoding used to encode point prompts, applied to a dense set of points the shape of the image encoding.

:param img: H W C int :param mask: H W int :param seq: aug_pipe :return:img H W C int mask H W int

@value: bs, sum(h, w), num_head, dim @sampling_locations: bs, sum(h, w), num_head, num_layer, 4, 2 @attention_weights: bs, sum(h, w), num

Resets the image embeddings and other state variables.

Convenience function to navigate between different tables that have one-to-one relations. E.g. we can use this function to convenient

Remove the non-conditioning memory around the input frame. When users provide correction clicks, the surrounding frames' non-conditio

Encode the current image and its prediction into a memory feature.

Forward SAM prompt encoders and mask heads. Inputs: - backbone_features: image features of [B, C, H, W] shape - poin