MCPcopy Create free account

hub / github.com/UCSB-VRL/WildlifeMapper / functions

Functions241 in github.com/UCSB-VRL/WildlifeMapper

⨍ Functions 241◇ Types & classes 46
↓ 22 callersMethoditems
(self)
wildlifemapper/segment_anything/utils/amg.py:41
↓ 19 callersMethodto
(self, device)
wildlifemapper/segment_anything/utils/misc.py:20
↓ 18 callersMethodcat
(self, new_stats: "MaskData")
wildlifemapper/segment_anything/utils/amg.py:59
↓ 17 callersFunctionprint
(*args, **kwargs)
wildlifemapper/train_utils.py:37
↓ 14 callersMethodmax
(self)
wildlifemapper/segment_anything/utils/misc.py:264
↓ 7 callersMethodupdate
(self, **kwargs)
wildlifemapper/segment_anything/utils/misc.py:292
↓ 5 callersMethod__init__
Args: dim (int): Number of input channels. num_heads (int): Number of attention heads in each ViT block.
wildlifemapper/segment_anything/modeling/image_encoder.py:143
↓ 5 callersFunctionprint
(*args, **kwargs)
wildlifemapper/segment_anything/utils/misc.py:107
↓ 4 callersFunctionbuild_dataset
(image_set, args)
wildlifemapper/dataloader_coco.py:320
↓ 4 callersMethodget_dense_pe
Returns the positional encoding used to encode point prompts, applied to a dense set of points the shape of the image encoding.
wildlifemapper/segment_anything/modeling/pos_encoder.py:24
↓ 4 callersMethodget_preprocess_shape
Compute the output size given input size and target long side length.
wildlifemapper/segment_anything/utils/transforms.py:91
↓ 3 callersFunction_build_sam
( encoder_embed_dim, encoder_depth, encoder_num_heads, encoder_global_attn_indexes, checkp
wildlifemapper/segment_anything/build_sam.py:242
↓ 3 callersMethod_pe_encoding
Positionally encode points that are normalized to [0,1].
wildlifemapper/segment_anything/modeling/pos_encoder.py:50
↓ 3 callersMethod_separate_heads
(self, x: Tensor, num_heads: int)
wildlifemapper/segment_anything/modeling/transformer.py:208
↓ 3 callersMethodadd_meter
(self, name, meter)
wildlifemapper/segment_anything/utils/misc.py:319
↓ 3 callersFunctioncrop
(image, target, region)
wildlifemapper/segment_anything/utils/augmentation.py:17
↓ 3 callersFunctionget_world_size
()
wildlifemapper/segment_anything/utils/misc.py:145
↓ 3 callersFunctionis_dist_avail_and_initialized
()
wildlifemapper/train_utils.py:58
↓ 3 callersFunctionis_dist_avail_and_initialized
()
wildlifemapper/segment_anything/utils/misc.py:138
↓ 3 callersMethodprepare
(self, predictions, iou_type)
wildlifemapper/inference.py:139
↓ 2 callersMethod__init__
( self, input_dim: int, hidden_dim: int, output_dim: int, num_layers:
wildlifemapper/segment_anything/modeling/box_decoder.py:155
↓ 2 callersMethod__init__
( self, embedding_dim: int, num_heads: int, downsample_rate: int = 1, )
wildlifemapper/segment_anything/modeling/transformer.py:191
↓ 2 callersMethod_get_src_permutation_idx
(self, indices)
wildlifemapper/segment_anything/build_sam.py:149
↓ 2 callersMethod_pe_encoding
Positionally encode points that are normalized to [0,1].
wildlifemapper/segment_anything/modeling/prompt_encoder.py:186
↓ 2 callersMethodapply_coords
Expects a numpy array of length 2 in the final dimension. Requires the original image size in (H, W) format.
wildlifemapper/segment_anything/utils/transforms.py:30
↓ 2 callersFunctionbox_cxcywh_to_xyxy
(x)
wildlifemapper/segment_anything/utils/box_ops.py:9
↓ 2 callersFunctioncalculate_stability_score
Computes the stability score for a batch of masks. The stability score is the IoU between the binary masks obtained by thresholding the p
wildlifemapper/segment_anything/utils/amg.py:156
↓ 2 callersFunctionconvert_to_xywh
(boxes)
wildlifemapper/inference.py:235
↓ 2 callersFunctioncrop_len
(orig_len, n_crops, overlap)
wildlifemapper/segment_anything/utils/amg.py:215
↓ 2 callersMethodforward_with_coords
Positionally encode points that are not normalized to [0,1].
wildlifemapper/segment_anything/modeling/prompt_encoder.py:208
↓ 2 callersMethodget_loss
(self, loss, outputs, targets, indices, num_boxes, **kwargs)
wildlifemapper/segment_anything/build_sam.py:161
↓ 2 callersFunctionget_rel_pos
Get relative positional embeddings according to the relative positions of query and key sizes. Args: q_size (int): size of qu
wildlifemapper/segment_anything/modeling/image_encoder.py:313
↓ 2 callersMethodlog_every
(self, iterable, print_freq, header=None)
wildlifemapper/segment_anything/utils/misc.py:322
↓ 2 callersFunctionnested_tensor_from_tensor_list
(tensor_list: List[Tensor])
wildlifemapper/segment_anything/utils/misc.py:46
↓ 2 callersMethodpostprocess_masks
Remove padding and upscale masks to the original image size. Arguments: masks (torch.Tensor): Batched masks from the mask_
wildlifemapper/segment_anything/modeling/sam.py:134
↓ 2 callersMethodpredict_masks
Predicts masks. See 'forwarself.output_upscalingd' for more details.
wildlifemapper/segment_anything/modeling/box_decoder.py:119
↓ 2 callersMethodpreprocess
Normalize pixel values and pad to a square input.
wildlifemapper/segment_anything/modeling/sam.py:165
↓ 2 callersMethodreset_image
Resets the currently set image.
wildlifemapper/segment_anything/predictor.py:262
↓ 2 callersFunctionresize
(image, target, size, max_size=None)
wildlifemapper/segment_anything/utils/augmentation.py:77
↓ 2 callersMethodsynchronize_between_processes
(self)
wildlifemapper/segment_anything/utils/misc.py:315
↓ 2 callersMethodupdate
(self, value, n=1)
wildlifemapper/segment_anything/utils/misc.py:231
↓ 1 callersMethod__getitem__
(self, idx)
wildlifemapper/dataloader_coco.py:33
↓ 1 callersMethod__init__
( self, embed_dim: int, image_embedding_size: Tuple[int, int], input_image_siz
wildlifemapper/segment_anything/modeling/pos_encoder.py:10
↓ 1 callersMethod__init__
( self, embedding_dim: int, mlp_dim: int, act: Type[nn.Module] = nn.GELU,
wildlifemapper/segment_anything/modeling/common.py:14
↓ 1 callersMethod__init__
Encodes prompts for input to SAM's mask decoder. Arguments: embed_dim (int): The prompts' embedding dimension im
wildlifemapper/segment_anything/modeling/prompt_encoder.py:17
↓ 1 callersMethod_embed_boxes
Embeds box prompts.
wildlifemapper/segment_anything/modeling/prompt_encoder.py:93
↓ 1 callersMethod_embed_masks
Embeds mask inputs.
wildlifemapper/segment_anything/modeling/prompt_encoder.py:102
↓ 1 callersMethod_embed_masks
(self, input_mask: torch.Tensor, has_mask_input: torch.Tensor)
wildlifemapper/segment_anything/utils/onnx.py:69
↓ 1 callersMethod_embed_points
Embeds point prompts.
wildlifemapper/segment_anything/modeling/prompt_encoder.py:73
↓ 1 callersMethod_embed_points
(self, point_coords: torch.Tensor, point_labels: torch.Tensor)
wildlifemapper/segment_anything/utils/onnx.py:51
↓ 1 callersFunction_evaluate
Run per image evaluation on given images and store results (a list of dict) in self.evalImgs :return: None
wildlifemapper/inference.py:278
↓ 1 callersMethod_get_batch_size
Gets the batch size of the output given the batch size of the input prompts.
wildlifemapper/segment_anything/modeling/prompt_encoder.py:107
↓ 1 callersMethod_get_device
(self)
wildlifemapper/segment_anything/modeling/prompt_encoder.py:125
↓ 1 callersMethod_recombine_heads
(self, x: Tensor)
wildlifemapper/segment_anything/modeling/transformer.py:213
↓ 1 callersMethodaccumulate
(self)
wildlifemapper/inference.py:130
↓ 1 callersFunctionaccuracy
Computes the precision@k for the specified values of k
wildlifemapper/segment_anything/utils/misc.py:83
↓ 1 callersFunctionadd_decomposed_rel_pos
Calculate decomposed Relative Positional Embeddings from :paper:`mvitv2`. https://github.com/facebookresearch/mvit/blob/19786631e330df9f3622e
wildlifemapper/segment_anything/modeling/image_encoder.py:346
↓ 1 callersMethodapply_boxes
Expects a numpy array shape Bx4. Requires the original image size in (H, W) format.
wildlifemapper/segment_anything/utils/transforms.py:44
↓ 1 callersMethodapply_coords_torch
Expects a torch tensor with length 2 in the last dimension. Requires the original image size in (H, W) format.
wildlifemapper/segment_anything/utils/transforms.py:64
↓ 1 callersMethodapply_image
Expects a numpy array with shape HxWxC in uint8 format.
wildlifemapper/segment_anything/utils/transforms.py:23
↓ 1 callersFunctionbox_candidates
(box1, box2, wh_thr=2, ar_thr=100, area_thr=0.1, eps=1e-16)
wildlifemapper/segment_anything/utils/augmentation_yolo.py:94
↓ 1 callersFunctionbox_iou
(boxes1, boxes2)
wildlifemapper/segment_anything/utils/box_ops.py:24
↓ 1 callersFunctionbox_xyxy_to_cxcywh
(x)
wildlifemapper/segment_anything/utils/box_ops.py:16
↓ 1 callersFunctionbuild_matcher
(args)
wildlifemapper/segment_anything/modeling/matcher.py:84
↓ 1 callersFunctionbuild_point_grid
Generates a 2D grid of points evenly spaced in [0,1]x[0,1].
wildlifemapper/segment_anything/utils/amg.py:179
↓ 1 callersFunctioncreate_common_coco_eval
(coco_eval, img_ids, eval_imgs)
wildlifemapper/inference.py:262
↓ 1 callersMethoddevice
(self)
wildlifemapper/segment_anything/modeling/sam.py:51
↓ 1 callersFunctionevaluate
(model, criterion, postprocessors, data_loader, base_ds, device, args)
wildlifemapper/inference.py:30
↓ 1 callersMethodfft
(self, img, rate=0.125)
wildlifemapper/segment_anything/network.py:36
↓ 1 callersFunctiongeneralized_box_iou
Generalized IoU from https://giou.stanford.edu/ The boxes should be in [x0, y0, x1, y1] format Returns a [N, M] pairwise matrix, where
wildlifemapper/segment_anything/utils/box_ops.py:40
↓ 1 callersFunctionget_coco_api_from_dataset
(dataset)
wildlifemapper/inference.py:20
↓ 1 callersFunctionget_rank
()
wildlifemapper/train_utils.py:44
↓ 1 callersFunctionget_size
(image_size, size, max_size=None)
wildlifemapper/segment_anything/utils/augmentation.py:100
↓ 1 callersFunctionget_size_with_aspect_ratio
(image_size, size, max_size=None)
wildlifemapper/segment_anything/utils/augmentation.py:80
↓ 1 callersFunctionhflip
(image, target)
wildlifemapper/segment_anything/utils/augmentation.py:60
↓ 1 callersFunctionis_main_process
()
wildlifemapper/train_utils.py:50
↓ 1 callersMethodload_mosaic
(self, index)
wildlifemapper/dataloader_coco.py:98
↓ 1 callersMethodltrb2cxcywh
(self, boxes)
wildlifemapper/dataloader_coco.py:193
↓ 1 callersFunctionmain
()
wildlifemapper/train.py:192
↓ 1 callersFunctionmake_coco_transforms
(image_set)
wildlifemapper/dataloader_coco.py:275
↓ 1 callersMethodmask_postprocessing
(self, masks: torch.Tensor, orig_im_size: torch.Tensor)
wildlifemapper/segment_anything/utils/onnx.py:76
↓ 1 callersFunctionmerge
(img_ids, eval_imgs)
wildlifemapper/inference.py:240
↓ 1 callersFunctionpad
(image, target, padding)
wildlifemapper/segment_anything/utils/augmentation.py:136
↓ 1 callersFunctionplot_points
(image, labels, boxes, image_id)
wildlifemapper/visualize_prediction.py:118
↓ 1 callersMethodpredict_torch
Predict masks for the given input prompts, using the currently set image. Input prompts are batched torch tensors and are expected to
wildlifemapper/segment_anything/predictor.py:169
↓ 1 callersMethodprepare_for_coco_detection
(self, predictions)
wildlifemapper/inference.py:149
↓ 1 callersMethodprepare_for_coco_keypoint
(self, predictions)
wildlifemapper/inference.py:208
↓ 1 callersMethodprepare_for_coco_segmentation
(self, predictions)
wildlifemapper/inference.py:173
↓ 1 callersFunctionrandom_perspective
(im, targets=(), degrees=10, translate=.1
wildlifemapper/segment_anything/utils/augmentation_yolo.py:107
↓ 1 callersMethodresize_longest_image_size
( input_image_size: torch.Tensor, longest_side: int )
wildlifemapper/segment_anything/utils/onnx.py:42
↓ 1 callersMethodselect_masks
( self, masks: torch.Tensor, iou_preds: torch.Tensor, num_points: int )
wildlifemapper/segment_anything/utils/onnx.py:92
↓ 1 callersMethodset_torch_image
Calculates the image embeddings for the provided image, allowing masks to be predicted with the 'predict' method. Expects the input
wildlifemapper/segment_anything/predictor.py:63
↓ 1 callersFunctionsetup_for_distributed
This function disables printing when not in master process
wildlifemapper/train_utils.py:30
↓ 1 callersFunctionsetup_for_distributed
This function disables printing when not in master process
wildlifemapper/segment_anything/utils/misc.py:100
↓ 1 callersFunctionshow_box
(box, ax)
wildlifemapper/train.py:118
↓ 1 callersMethodsummarize
(self)
wildlifemapper/inference.py:134
↓ 1 callersMethodsynchronize_between_processes
(self)
wildlifemapper/inference.py:125
↓ 1 callersFunctionuncrop_boxes_xyxy
(boxes: torch.Tensor, crop_box: List[int])
wildlifemapper/segment_anything/utils/amg.py:237
↓ 1 callersMethodupdate
(self, predictions)
wildlifemapper/inference.py:106
↓ 1 callersFunctionwindow_partition
Partition into non-overlapping windows with padding if needed. Args: x (tensor): input tokens with [B, H, W, C]. window_size
wildlifemapper/segment_anything/modeling/image_encoder.py:264
next →1–100 of 241, ranked by callers