MCPcopy Create free account

hub / github.com/OpenGVLab/UniFormerV2 / functions

Functions872 in github.com/OpenGVLab/UniFormerV2

⨍ Functions 872◇ Types & classes 124
Method__init__
(self, inplanes, planes, stride=1)
extract_clip/model.py:13
Method__init__
(self, spacial_dim: int, embed_dim: int, num_heads: int, output_dim: int = None)
extract_clip/model.py:59
Method__init__
(self, layers, output_dim, heads, input_resolution=224, width=64)
extract_clip/model.py:102
Method__init__
(self, d_model: int, n_head: int, attn_mask: torch.Tensor = None)
extract_clip/model.py:172
Method__init__
(self, width: int, layers: int, heads: int, attn_mask: torch.Tensor = None)
extract_clip/model.py:196
Method__init__
(self, input_resolution: int, patch_size: int, width: int, layers: int, heads: int, output_dim: int)
extract_clip/model.py:207
Method__init__
overall_iters (int): the overall number of iterations of one epoch. cfg (CfgNode): configs. mode (str): `train`, `val`, or `t
slowfast/utils/meters.py:51
Method__init__
Construct tensors to store the predictions and labels. Expect to get num_clips predictions from each video, and calculate the metrics
slowfast/utils/meters.py:239
Method__init__
Args: window_size (int): size of the max length of the deque.
slowfast/utils/meters.py:414
Method__init__
Args: epoch_iters (int): the overall number of iterations of one epoch. cfg (CfgNode): configs.
slowfast/utils/meters.py:463
Method__init__
Args: max_iter (int): the max number of iteration of the current epoch. cfg (CfgNode): configs.
slowfast/utils/meters.py:607
Method__init__
(self)
slowfast/utils/meters.py:786
Method__init__
(self, model, decay=0.9999, device=None)
slowfast/utils/ema.py:91
Method__init__
overall_iters (int): the overall number of iterations of one epoch. cfg (CfgNode): configs. mode (str): `train`, `val`, or `t
slowfast/utils/meters_co.py:51
Method__init__
Construct tensors to store the predictions and labels. Expect to get num_clips predictions from each video, and calculate the metrics
slowfast/utils/meters_co.py:239
Method__init__
Args: window_size (int): size of the max length of the deque.
slowfast/utils/meters_co.py:414
Method__init__
Args: epoch_iters (int): the overall number of iterations of one epoch. cfg (CfgNode): configs.
slowfast/utils/meters_co.py:463
Method__init__
Args: max_iter (int): the max number of iteration of the current epoch. cfg (CfgNode): configs.
slowfast/utils/meters_co.py:615
Method__init__
(self)
slowfast/utils/meters_co.py:795
Method__init__
Constructs box collection. Args: data: a numpy array of shape [N, 4] representing box coordinates Raises: ValueE
slowfast/utils/ava_evaluation/np_box_list.py:39
Method__init__
Initialized PerImageEvaluation by evaluation parameters. Args: num_groundtruth_classes: Number of ground truth object classes
slowfast/utils/ava_evaluation/per_image_evaluation.py:42
Method__init__
Constructs box collection. Args: box_data: a numpy array of shape [N, 4] representing box coordinates mask_data: a numpy
slowfast/utils/ava_evaluation/np_box_mask_list.py:37
Method__init__
Constructor. Args: categories: A list of dicts, each of which has the following keys - 'id': (required) an integer id u
slowfast/utils/ava_evaluation/object_detection_evaluation.py:110
Method__init__
(self, categories, matching_iou_threshold=0.5)
slowfast/utils/ava_evaluation/object_detection_evaluation.py:360
Method__init__
(self, categories, matching_iou_threshold=0.5)
slowfast/utils/ava_evaluation/object_detection_evaluation.py:384
Method__init__
(self, categories, matching_iou_threshold=0.5)
slowfast/utils/ava_evaluation/object_detection_evaluation.py:397
Method__init__
(self, categories, matching_iou_threshold=0.5)
slowfast/utils/ava_evaluation/object_detection_evaluation.py:422
Method__init__
Constructor. Args: categories: A list of dicts, each of which has the following keys - 'id': (required) an integer id u
slowfast/utils/ava_evaluation/object_detection_evaluation.py:440
Method__init__
( self, num_groundtruth_classes, matching_iou_threshold=0.5, nms_iou_threshold
slowfast/utils/ava_evaluation/object_detection_evaluation.py:537
Method__init__
Predict Worker for Detectron2. Args: cfg (CfgNode): configs. Details can be found in slow
slowfast/visualization/async_predictor.py:19
Method__init__
(self, cfg, result_queue=None)
slowfast/visualization/async_predictor.py:54
Method__init__
Visualization Worker for AsyncVis. Args: video_vis (VideoVisualizer object): object with tools for visualizat
slowfast/visualization/async_predictor.py:128
Method__init__
Args: cfg (CfgNode): configs. Details can be found in slowfast/config/defaults.py async_vis (AsyncVis
slowfast/visualization/async_predictor.py:242
Method__init__
Args: cfg (CfgNode): configs. Details can be found in slowfast/config/defaults.py
slowfast/visualization/demo_loader.py:22
Method__init__
Args: cfg (CfgNode): configs. Details can be found in slowfast/config/defaults.py
slowfast/visualization/demo_loader.py:153
Method__init__
Args: cfg (CfgNode): configs. Details can be found in slowfast/config/defaults.py
slowfast/visualization/tensorboard_vis.py:25
Method__init__
Args: cfg (CfgNode): configs. Details can be found in slowfast/config/defaults.py gpu_id (Optional[in
slowfast/visualization/predictor.py:25
Method__init__
Args: model (nn.Module): the model containing layers to obtain weights and activations from. layers (list of strings)
slowfast/visualization/utils.py:163
Method__init__
(self)
slowfast/visualization/utils.py:344
Method__init__
Args: model (model): the model to be used. target_layers (list of str(s)): name of convolutional layer to be used to
slowfast/visualization/gradcam_utils.py:20
Method__init__
Args: cfg (CfgNode): configs. Details can be found in slowfast/config/defaults.py
slowfast/visualization/ava_demo_precomputed_boxes.py:30
Method__init__
Construct the Kinetics video loader with a given csv file. The format of the csv file is: ``` path_to_video_1 label_1
slowfast/datasets/kinetics.py:35
Method__init__
Construct the MiT video loader with a given csv file. The format of the csv file is: ``` path_to_video_1 label_1
slowfast/datasets/mit.py:34
Method__init__
(self, cfg, split)
slowfast/datasets/ava_dataset.py:23
Method__init__
(self, cfg, mode, num_retries=10)
slowfast/datasets/imagenet.py:35
Method__init__
(self, sampler, batch_size, drop_last, cfg)
slowfast/datasets/multigrid_helper.py:26
Method__init__
Construct the Kinetics video loader with a given csv file. The format of the csv file is: ``` path_to_video_1 label_1
slowfast/datasets/kinetics_sparse.py:35
Method__init__
( self, size, scale=(0.08, 1.0), ratio=(3.0 / 4.0, 4.0 / 3.0), interpo
slowfast/datasets/transform.py:741
Method__init__
Args: mixup_alpha (float): Mixup alpha value. cutmix_alpha (float): Cutmix alpha value. mix_prob (float):
slowfast/datasets/mixup.py:117
Method__init__
Construct the dataset. Args: num_vidoes (int): number of videos in the dataset. clips_per_video (int): numbe
slowfast/datasets/ptv_datasets.py:47
Method__init__
(self, num_clips, num_crops)
slowfast/datasets/ptv_datasets.py:114
Method__init__
Construct the ANet video loader with a given csv file. The format of the csv file is: ``` path_to_video_1 total_time_
slowfast/datasets/anet.py:34
Method__init__
(self, name, prob=0.5, magnitude=10, hparams=None)
slowfast/datasets/rand_augment.py:344
Method__init__
(self, ops, num_layers=2, choice_weights=None)
slowfast/datasets/rand_augment.py:465
Method__init__
Load Charades data (frame paths, labels, etc. ) to a given Dataset object. The dataset could be downloaded from Chrades official webs
slowfast/datasets/charades.py:31
Method__init__
Load Something-Something data (frame paths, labels, etc. ) to a given Dataset object. The dataset could be downloaded from Something-
slowfast/datasets/sth.py:35
Method__init__
( self, probability=0.5, min_area=0.02, max_area=1 / 3, min_aspect=0.3
slowfast/datasets/random_erasing.py:53
Method__init__
Args: dim (int): number of dimension for the input. dim_inner (int): number of dimension inside of the Non-local bloc
slowfast/models/nonlocal_helper.py:20
Method__init__
The `__init__` method of any subclass should also contain these arguments. Args: cfg (CfgNode): model buildi
slowfast/models/ptv_model_builder.py:61
Method__init__
The `__init__` method of any subclass should also contain these arguments. Args: cfg (CfgNode): model buildi
slowfast/models/ptv_model_builder.py:224
Method__init__
The `__init__` method of any subclass should also contain these arguments. Args: cfg (CfgNode): model buildi
slowfast/models/ptv_model_builder.py:526
Method__init__
The `__init__` method of any subclass should also contain these arguments. Args: cfg (CfgNode): model buildi
slowfast/models/ptv_model_builder.py:611
Method__init__
Naive version of Synchronized 3D BatchNorm. Args: num_sync_devices (int): number of device to sync. args (lis
slowfast/models/batchnorm_helper.py:175
Method__init__
(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0.)
slowfast/models/uniformer.py:69
Method__init__
(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.)
slowfast/models/uniformer.py:97
Method__init__
(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0., dr
slowfast/models/uniformer.py:116
Method__init__
(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0., dr
slowfast/models/uniformer.py:138
Method__init__
(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0., dr
slowfast/models/uniformer.py:164
Method__init__
(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768)
slowfast/models/uniformer.py:204
Method__init__
(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768, std=False)
slowfast/models/uniformer.py:231
Method__init__
(self, cfg)
slowfast/models/uniformer.py:264
Method__init__
Args: dim_in (int): the channel dimension of the input. fusion_conv_channel_ratio (int): channel ratio for the convol
slowfast/models/video_model_builder.py:103
Method__init__
The `__init__` method of any subclass should also contain these arguments. Args: cfg (CfgNode): model buildin
slowfast/models/video_model_builder.py:166
Method__init__
The `__init__` method of any subclass should also contain these arguments. Args: cfg (CfgNode): model buildi
slowfast/models/video_model_builder.py:437
Method__init__
(self, cfg)
slowfast/models/video_model_builder.py:772
Method__init__
(self, d_model, dw_reduction=1.5, pos_kernel_size=3)
slowfast/models/uniformerv2_model.py:41
Method__init__
( self, d_model, n_head, attn_mask=None, drop_path=0.0, dw_reduction=1.5, no_lmhra=Fa
slowfast/models/uniformerv2_model.py:63
Method__init__
( self, width, layers, heads, attn_mask=None, backbone_drop_path_rate=0., use_checkpo
slowfast/models/uniformerv2_model.py:186
Method__init__
( self, # backbone input_resolution, patch_size, width, layers, heads, output_dim, ba
slowfast/models/uniformerv2_model.py:278
Method__init__
Args: reduction (str): specifies reduction to apply to the output. It can be "mean" (default) or "none".
slowfast/models/losses.py:16
Method__init__
Args: dim_in (int): the channel dimensions of the input. dim_out (int): the channel dimension of the output.
slowfast/models/resnet_helper.py:34
Method__init__
Args: dim_in (int): the channel dimensions of the input. dim_out (int): the channel dimension of the output.
slowfast/models/resnet_helper.py:122
Method__init__
Args: dim_in (int): the channel dimensions of the input. dim_out (int): the channel dimension of the output.
slowfast/models/resnet_helper.py:262
Method__init__
The `__init__` method of any subclass should also contain these arguments. ResStage builds p streams, where p can be greater or equal
slowfast/models/resnet_helper.py:530
Method__init__
The `__init__` method of any subclass should also contain these arguments. List size of 1 for single pathway models (C2D, I3D, Slow
slowfast/models/stem_helper.py:26
Method__init__
The `__init__` method of any subclass should also contain these arguments. Args: dim_in (int): the channel dimension of
slowfast/models/stem_helper.py:132
Method__init__
( self, dim_in=3, dim_out=768, kernel=(1, 16, 16), stride=(1, 4, 4),
slowfast/models/stem_helper.py:295
Method__init__
(self, dims)
slowfast/models/common.py:38
Method__init__
(self, drop_prob=None)
slowfast/models/common.py:65
Method__init__
( self, dim, num_heads=8, qkv_bias=False, drop_rate=0.0, kerne
slowfast/models/attention.py:50
Method__init__
(self, cfg)
slowfast/models/uniformerv2.py:16
Method__init__
The `__init__` method of any subclass should also contain these arguments. ResNetBasicHead takes p pathways as input wher
slowfast/models/head_helper.py:142
Method__init__
Perform linear projection and activation as head for tranformers. Args: dim_in (int): the channel dimension of the input
slowfast/models/head_helper.py:368
Method__init__
(self)
slowfast/models/operators.py:13
Method__iter__
(self)
slowfast/visualization/demo_loader.py:67
Method__iter__
(self)
slowfast/visualization/demo_loader.py:226
Method__iter__
(self)
slowfast/datasets/multigrid_helper.py:68
Method__iter__
(self)
slowfast/datasets/ptv_datasets.py:90
Method__len__
Returns: (int): the number of videos in the dataset.
slowfast/datasets/kinetics.py:399
Method__len__
Returns: (int): the number of videos in the dataset.
slowfast/datasets/mit.py:407
← previousnext →401–500 of 872, ranked by callers