MCPcopy Create free account

hub / github.com/NVlabs/FoundationStereo / functions

Functions881 in github.com/NVlabs/FoundationStereo

⨍ Functions 881◇ Types & classes 190↳ Endpoints 1
↓ 1 callersMethod_iterator
(self)
dinov2/dinov2/data/samplers.py:104
↓ 1 callersMethod_iterator
(self)
dinov2/dinov2/data/samplers.py:201
↓ 1 callersMethod_load_entries_class_ids
(self, root: Optional[str] = None)
dinov2/dinov2/data/datasets/image_net_22k.py:141
↓ 1 callersMethod_load_labels
(self, labels_path: str)
dinov2/dinov2/data/datasets/image_net.py:171
↓ 1 callersFunction_make_dinov2_dpt_depth_head
(*, embed_dim: int, min_depth: float, max_depth: float)
dinov2/dinov2/hub/depthers.py:167
↓ 1 callersFunction_make_dinov2_linear_classification_head
( *, arch_name: str = "vit_large", patch_size: int = 14, embed_dim: int = 1024, layers: in
dinov2/dinov2/hub/classifiers.py:20
↓ 1 callersFunction_make_dinov2_linear_depth_head
( *, embed_dim: int, layers: int, min_depth: float, max_depth: float, **kwargs, )
dinov2/dinov2/hub/depthers.py:36
↓ 1 callersFunction_make_mmap_tarball
(tarballs_root: str, mmap_cache_size: int)
dinov2/dinov2/data/datasets/image_net_22k.py:59
↓ 1 callersFunction_make_sampler
( *, dataset, type: Optional[SamplerType] = None, shuffle: bool = False, seed: int = 0,
dinov2/dinov2/data/loaders.py:100
↓ 1 callersFunction_make_scratch
(in_shape, out_shape, groups=1, expand=False)
depth_anything/blocks.py:4
↓ 1 callersFunction_make_seed
(seed: int, start: int, iter_count: int)
dinov2/dinov2/data/samplers.py:160
↓ 1 callersMethod_mask
(self, mask, max_mask_patches)
dinov2/dinov2/data/masking.py:49
↓ 1 callersFunction_parse_dataset_str
(dataset_str: str)
dinov2/dinov2/data/loaders.py:44
↓ 1 callersMethod_parse_losses
Parse the raw outputs (losses) of the network. Args: losses (dict): Raw output of the network, which usually contain
dinov2/dinov2/eval/depth/models/depther/base.py:163
↓ 1 callersMethod_parse_losses
(losses)
dinov2/dinov2/hub/depth/encoder_decoder.py:318
↓ 1 callersFunction_parse_slurm_node_list
(s: str)
dinov2/dinov2/distributed/__init__.py:128
↓ 1 callersFunction_restrict_print_to_main_process
This function disables printing when not in the main process
dinov2/dinov2/distributed/__init__.py:74
↓ 1 callersMethod_sample_neg
Sample negative samples.
dinov2/dinov2/eval/segmentation_m2f/core/box/samplers/base_sampler.py:30
↓ 1 callersMethod_sample_pos
Sample positive samples.
dinov2/dinov2/eval/segmentation_m2f/core/box/samplers/base_sampler.py:25
↓ 1 callersMethod_set_from_local
(self)
dinov2/dinov2/distributed/__init__.py:210
↓ 1 callersMethod_set_from_preset_env
(self)
dinov2/dinov2/distributed/__init__.py:198
↓ 1 callersMethod_set_from_slurm_env
(self)
dinov2/dinov2/distributed/__init__.py:181
↓ 1 callersMethod_setup_args
(self)
dinov2/dinov2/run/eval/linear.py:35
↓ 1 callersMethod_setup_args
(self)
dinov2/dinov2/run/eval/log_regression.py:35
↓ 1 callersMethod_setup_args
(self)
dinov2/dinov2/run/eval/knn.py:35
↓ 1 callersMethod_setup_args
(self)
dinov2/dinov2/run/train/train.py:35
↓ 1 callersMethod_shuffled_iterator
(self)
dinov2/dinov2/data/samplers.py:111
↓ 1 callersMethod_shuffled_iterator
(self)
dinov2/dinov2/data/samplers.py:208
↓ 1 callersMethod_similarity_for_rank
(self, features_rank, source_rank)
dinov2/dinov2/eval/knn.py:129
↓ 1 callersMethod_transform_inputs
Transform inputs for decoder. Args: inputs (list[Tensor]): List of multi-level img features. Returns: Tensor:
dinov2/dinov2/eval/depth/models/decode_heads/linear_head.py:29
↓ 1 callersMethod_transform_inputs
Transform inputs for decoder. Args: inputs (list[Tensor]): List of multi-level img features. Returns: Tensor:
dinov2/dinov2/eval/segmentation/models/decode_heads/linear_head.py:42
↓ 1 callersMethod_transform_inputs
Transform inputs for decoder. Args: inputs (list[Tensor]): List of multi-level img features. Returns: Tensor:
dinov2/dinov2/hub/depth/decode_heads.py:237
↓ 1 callersFunctionadd_prefix
Add prefix for dict. Args: inputs (dict): The input dict with str keys. prefix (str): The prefix to add. Returns: d
dinov2/dinov2/eval/depth/models/depther/encoder_decoder.py:15
↓ 1 callersFunctionadd_prefix
Add prefix for dict. Args: inputs (dict): The input dict with str keys. prefix (str): The prefix to add. Returns: d
dinov2/dinov2/hub/depth/encoder_decoder.py:15
↓ 1 callersFunctionadd_residual
(x, brange, residual, residual_scale_factor, scaling_vector=None)
dinov2/dinov2/layers/block.py:205
↓ 1 callersMethodapply_center_update
(self)
dinov2/dinov2/loss/ibot_patch_loss.py:141
↓ 1 callersMethodapply_center_update
(self)
dinov2/dinov2/loss/dino_clstoken_loss.py:89
↓ 1 callersFunctionapply_optim_scheduler
(optimizer, lr, wd, last_layer_lr)
dinov2/dinov2/train/train.py:113
↓ 1 callersFunctionapply_scaling_rules_to_cfg
(cfg)
dinov2/dinov2/utils/config.py:21
↓ 1 callersFunctionas_torch_dtype
(dtype: TypeSpec)
dinov2/dinov2/utils/dtype.py:31
↓ 1 callersMethodassign
Assign boxes to either a ground truth boxes or a negative boxes.
dinov2/dinov2/eval/segmentation_m2f/models/utils/assigner.py:40
↓ 1 callersMethodaug_test
Placeholder for augmentation test.
dinov2/dinov2/eval/depth/models/depther/base.py:58
↓ 1 callersMethodaug_test
Test with augmentations. Only rescale=True is supported.
dinov2/dinov2/hub/depth/encoder_decoder.py:200
↓ 1 callersMethodbackprop_loss
(self, loss)
dinov2/dinov2/train/ssl_meta_arch.py:126
↓ 1 callersMethodbinary_mask_dice_loss
Args: mask_preds (Tensor): Mask prediction in shape (N1, H, W). gt_masks (Tensor): Ground truth in shape (N2, H, W)
dinov2/dinov2/eval/segmentation_m2f/models/losses/match_costs.py:71
↓ 1 callersFunctionbuild_assigner
Build Assigner.
dinov2/dinov2/eval/segmentation_m2f/models/builder.py:18
↓ 1 callersFunctionbuild_concat_volume
(refimg_fea, targetimg_fea, maxdisp)
core/submodule.py:412
↓ 1 callersFunctionbuild_gwc_volume
@refimg_fea: left image feature @targetimg_fea: right image feature
core/submodule.py:395
↓ 1 callersFunctionbuild_model
(args, only_teacher=False, img_size=224)
dinov2/dinov2/models/__init__.py:14
↓ 1 callersFunctionbuild_model_for_eval
(config, pretrained_weights)
dinov2/dinov2/eval/setup.py:62
↓ 1 callersFunctionbuild_optimizer
(cfg, params_groups)
dinov2/dinov2/train/train.py:61
↓ 1 callersFunctionbuild_prior_generator
(cfg, default_args=None)
dinov2/dinov2/eval/segmentation_m2f/core/anchor/builder.py:15
↓ 1 callersFunctionbuild_sampler
Builder of box sampler.
dinov2/dinov2/eval/segmentation_m2f/core/box/builder.py:12
↓ 1 callersFunctionbuild_schedulers
(cfg)
dinov2/dinov2/train/train.py:65
↓ 1 callersFunctionbuild_topk_imagenet_real_accuracy_metric
(num_classes: int, ks: tuple = (1, 5))
dinov2/dinov2/eval/metrics.py:66
↓ 1 callersMethodcompute
(self)
dinov2/dinov2/eval/metrics.py:111
↓ 1 callersMethodcompute_baseline
(self, left_id, right_id)
scripts/run_demo_batch.py:102
↓ 1 callersMethodcompute_neighbors
(self, features_rank)
dinov2/dinov2/eval/knn.py:162
↓ 1 callersFunctioncontext_upsample
@disp_low: (b,1,h,w) 1/4 resolution @up_weights: (b,9,4*h,4*w) Image resolution
core/submodule.py:452
↓ 1 callersMethodcorr
(fmap1, fmap2)
core/geometry.py:68
↓ 1 callersFunctioncreate_class_indices_mapping
(labels)
dinov2/dinov2/eval/knn.py:234
↓ 1 callersFunctioncreate_module_dict
(*, module, n_per_class_list, n_tries, nb_knn, train_features, train_labels)
dinov2/dinov2/eval/knn.py:198
↓ 1 callersFunctiondefault_setup
(args)
dinov2/dinov2/utils/config.py:49
↓ 1 callersFunctiondeform_inputs
(x, patch_size)
dinov2/dinov2/eval/segmentation_m2f/models/backbones/adapter_modules.py:32
↓ 1 callersMethoddepth2xyzmap
(self, depth, K)
scripts/run_demo_batch.py:127
↓ 1 callersFunctiondepth_uint8_decoding
(depth_uint8, scale=1000)
Utils.py:137
↓ 1 callersFunctiondice_loss
Calculate dice loss, which is proposed in `V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation <https://arxiv
dinov2/dinov2/eval/segmentation_m2f/models/losses/dice_loss.py:12
↓ 1 callersFunctiondinov2_vitl14_reg
DINOv2 ViT-L/14 model with registers (optionally) pretrained on the LVD-142M dataset.
dinov2/dinov2/hub/backbones.py:128
↓ 1 callersFunctiondisparity_regression
(x, maxdisp)
core/submodule.py:427
↓ 1 callersFunctiondo_train
(cfg, model, resume=False)
dinov2/dinov2/train/train.py:134
↓ 1 callersFunctiondrop_path
(x, drop_prob: float = 0.0, training: bool = False)
dinov2/dinov2/eval/segmentation_m2f/models/backbones/drop_path.py:13
↓ 1 callersFunctiondrop_path
(x, drop_prob: float = 0.0, training: bool = False)
dinov2/dinov2/layers/drop_path.py:14
↓ 1 callersMethoddump_in_output_file
(self, iteration, iter_time, data_time)
dinov2/dinov2/logging/helpers.py:53
↓ 1 callersFunctioneval_knn
( model, train_dataset, val_dataset, accuracy_averaging, nb_knn, temperature, batc
dinov2/dinov2/eval/knn.py:245
↓ 1 callersFunctioneval_knn_with_model
( model, output_dir, train_dataset_str="ImageNet:split=TRAIN", val_dataset_str="ImageNet:split
dinov2/dinov2/eval/knn.py:318
↓ 1 callersFunctioneval_linear
( *, feature_model, linear_classifiers, train_data_loader, val_data_loader, metrics_fi
dinov2/dinov2/eval/linear.py:313
↓ 1 callersFunctioneval_log_regression
Implements the "standard" process for log regression evaluation: The value of C is chosen by training on train_dataset and evaluating on
dinov2/dinov2/eval/log_regression.py:252
↓ 1 callersFunctioneval_log_regression_with_model
( model, train_dataset_str="ImageNet:split=TRAIN", val_dataset_str="ImageNet:split=VAL", finet
dinov2/dinov2/eval/log_regression.py:362
↓ 1 callersFunctionextract_features_with_dataloader
(model, data_loader, sample_count, gather_on_cpu=False)
dinov2/dinov2/eval/utils.py:113
↓ 1 callersFunctionfilter_train
(mapping, n_per_class, seed)
dinov2/dinov2/eval/knn.py:225
↓ 1 callersMethodfit
(self, train_features, train_labels)
dinov2/dinov2/eval/log_regression.py:137
↓ 1 callersMethodforward
(self, x)
core/extractor.py:349
↓ 1 callersMethodforward
(self, x: Tensor)
dinov2/dinov2/layers/block.py:89
↓ 1 callersMethodforward
(self, x: Tensor, is_causal: bool = False)
dinov2/dinov2/layers/attention.py:69
↓ 1 callersMethodforward_backward
(self, images, teacher_temp)
dinov2/dinov2/train/ssl_meta_arch.py:132
↓ 1 callersMethodforward_features
(self, x)
dinov2/dinov2/eval/segmentation_m2f/models/backbones/vit.py:508
↓ 1 callersMethodforward_features_list
(self, x_list, masks_list)
dinov2/dinov2/models/vision_transformer.py:235
↓ 1 callersMethodforward_masked
( self, student_patch_tokens_masked, teacher_patch_tokens_masked, student_mask
dinov2/dinov2/loss/ibot_patch_loss.py:105
↓ 1 callersMethodforward_nested
x_list contains a list of tensors to nest together and run
dinov2/dinov2/layers/block.py:268
↓ 1 callersMethodforward_test
Test segment without test-time aumengtation. Only the output of last decoder layers was used. Args: inputs (list[Tensor]
dinov2/dinov2/eval/segmentation_m2f/models/decode_heads/mask2former_head.py:522
↓ 1 callersMethodforward_train
Placeholder for Forward function for training.
dinov2/dinov2/eval/depth/models/depther/base.py:48
↓ 1 callersMethodforward_train
Forward function for training. Args: img (Tensor): Input images. img_metas (list[dict]): List of image info dict wher
dinov2/dinov2/eval/depth/models/depther/encoder_decoder.py:105
↓ 1 callersFunctionfree_if_fsdp
(x)
dinov2/dinov2/fsdp/__init__.py:65
↓ 1 callersFunctionfreeze_model
(model)
Utils.py:79
↓ 1 callersMethodfsdp_synchronize_streams
(self)
dinov2/dinov2/train/ssl_meta_arch.py:348
↓ 1 callersFunctionfuse_params_groups
(all_params_groups, keys=("lr_multiplier", "wd_multiplier", "is_last_layer"))
dinov2/dinov2/utils/param_groups.py:92
↓ 1 callersMethodgen_encoder_output_proposals
Generate proposals from encoded memory. Args: memory (Tensor) : The output of encoder, has shape (bs, num_key, em
dinov2/dinov2/eval/segmentation_m2f/models/utils/transformer.py:636
↓ 1 callersFunctionget_args_parser
( description: Optional[str] = None, parents: Optional[List[argparse.ArgumentParser]] = None, add_
dinov2/dinov2/eval/linear.py:33
↓ 1 callersFunctionget_args_parser
( description: Optional[str] = None, parents: Optional[List[argparse.ArgumentParser]] = None, add_
dinov2/dinov2/eval/log_regression.py:38
↓ 1 callersFunctionget_args_parser
( description: Optional[str] = None, parents: Optional[List[argparse.ArgumentParser]] = None, add_
dinov2/dinov2/eval/knn.py:29
← previousnext →201–300 of 881, ranked by callers