MCPcopy Create free account

hub / github.com/Picsart-AI-Research/Text2Video-Zero / functions

Functions1,788 in github.com/Picsart-AI-Research/Text2Video-Zero

Methodlog
(self, runner)
annotator/uniformer/mmcv/runner/hooks/logger/pavi.py:82
Methodlog
(self, runner)
annotator/uniformer/mmcv/runner/hooks/logger/mlflow.py:70
Methodlog
(self, runner)
annotator/uniformer/mmcv/runner/hooks/logger/dvclive.py:54
Functionlogo_name_to_path
(name)
gradio_utils.py:90
Methodloss_scale
(self)
annotator/uniformer/mmcv/runner/fp16_utils.py:409
Methodlosses
Compute segmentation and semantic encoding loss.
annotator/uniformer/mmseg/models/decode_heads/enc_head.py:178
Functionlovasz_hinge
Binary Lovasz hinge loss. Args: logits (torch.Tensor): [B, H, W], logits at each pixel (between -infty and +infty). l
annotator/uniformer/mmseg/models/losses/lovasz_loss.py:83
Functionlovasz_softmax
Multi-class Lovasz-Softmax loss. Args: probs (torch.Tensor): [B, C, H, W], class probabilities at each prediction (between 0
annotator/uniformer/mmseg/models/losses/lovasz_loss.py:171
Functionlut_transform
Transform array by look-up table. The function lut_transform fills the output array with values from the look-up table. Indices of the entrie
annotator/uniformer/mmcv/image/photometric.py:381
Methodmake_res_layer
Pack all blocks in a stage into a ``ResLayer``.
annotator/uniformer/mmseg/models/backbones/resnest.py:305
Methodmake_res_layer
Pack all blocks in a stage into a ``ResLayer``
annotator/uniformer/mmseg/models/backbones/resnext.py:139
Functionmask_cross_entropy
Calculate the CrossEntropy loss for masks. Args: pred (torch.Tensor): The prediction with shape (N, C), C is the number of cl
annotator/uniformer/mmseg/models/losses/cross_entropy_loss.py:100
Functionmaster_only
(func)
annotator/uniformer/mmcv/runner/dist_utils.py:88
Methodmax_epochs
int: Maximum training epochs.
annotator/uniformer/mmcv/runner/base_runner.py:175
Methodmax_iters
int: Maximum training iterations.
annotator/uniformer/mmcv/runner/base_runner.py:180
Functionmean_dice
Calculate Mean Dice (mDice) Args: results (list[ndarray] | list[str]): List of prediction segmentation maps or list of predic
annotator/uniformer/mmseg/core/evaluation/metrics.py:172
Functionmean_fscore
Calculate Mean Intersection and Union (mIoU) Args: results (list[ndarray] | list[str]): List of prediction segmentation maps
annotator/uniformer/mmseg/core/evaluation/metrics.py:212
Functionmean_iou
Calculate Mean Intersection and Union (mIoU) Args: results (list[ndarray] | list[str]): List of prediction segmentation maps
annotator/uniformer/mmseg/core/evaluation/metrics.py:133
Methodmerge_from_dict
Merge list into cfg_dict. Merge the dict parsed by MultipleKVAction into this cfg. Examples: >>> options = {'model.backb
annotator/uniformer/mmcv/utils/config.py:550
Methodmodel_name
str: Name of the model, usually the module class name.
annotator/uniformer/mmcv/runner/base_runner.py:139
Methodmodule_dict
(self)
annotator/uniformer/mmcv/utils/registry.py:179
Functionmotion_to_video_path
(motion)
gradio_utils.py:30
Functionmulti_gpu_test
Test model with multiple gpus. This method tests model with multiple gpus and collects the results under two different modes: gpu and cpu mod
annotator/uniformer/mmcv/engine/test.py:44
Methodname
(self)
annotator/uniformer/mmcv/utils/registry.py:171
Methodname
(self)
annotator/uniformer/mmcv/fileio/file_client.py:31
Methodname
(self)
annotator/uniformer/mmcv/fileio/file_client.py:823
Functionnew_forward
(*args, **kwargs)
annotator/uniformer/mmcv/runner/fp16_utils.py:296
Functionnew_func
(*args, **kwargs)
annotator/uniformer/mmcv/utils/misc.py:304
Functionnew_func
(*args, **kwargs)
annotator/uniformer/mmcv/runner/fp16_utils.py:91
Functionnms
Dispatch to either CPU or GPU NMS implementations. The input can be either torch tensor or numpy array. GPU NMS will be used if the input is
annotator/uniformer/mmcv/ops/nms.py:118
Functionnms_bev
NMS function GPU implementation (for BEV boxes). The overlap of two boxes for IoU calculation is defined as the exact overlapping area of the
annotator/uniformer/mmcv/ops/iou3d.py:31
Functionnms_match
Matched dets into different groups by NMS. NMS match is Similar to NMS but when a bbox is suppressed, nms match will record the indice of sup
annotator/uniformer/mmcv/ops/nms.py:339
Functionnms_normal_bev
Normal NMS function GPU implementation (for BEV boxes). The overlap of two boxes for IoU calculation is defined as the exact overlapping area of
annotator/uniformer/mmcv/ops/iou3d.py:65
Functionnms_rotated
Performs non-maximum suppression (NMS) on the rotated boxes according to their intersection-over-union (IoU). Rotated NMS iteratively removes
annotator/uniformer/mmcv/ops/nms.py:376
Methodno_weight_decay
(self)
annotator/uniformer/mmseg/models/backbones/uniformer.py:373
Functionnorm_flops_counter_hook
(module, input, output)
annotator/uniformer/mmcv/cnn/utils/flops_counter.py:430
Functionnpmax
(array)
annotator/openpose/util.py:159
Functionobj_from_dict
Initialize an object from dict. The dict must contain the key "type", which indicates the object type, it can be either a string or type, suc
annotator/uniformer/mmcv/runner/utils.py:35
Functionon_canny_selection_update
(evt: gr.EventData)
app_canny_db.py:107
Functionon_db_selection_update
(evt: gr.EventData)
app_canny_db.py:102
Functionon_video_path_update
(evt: gr.EventData)
app_pose.py:73
Methodopened
bool: Indicate whether the video is opened.
annotator/uniformer/mmcv/video/io.py:85
FunctionpadRightDownCorner
(img, stride, padValue)
annotator/openpose/util.py:7
Methodpad_dims
(self)
annotator/uniformer/mmcv/parallel/data_container.py:80
Methodpadding_value
(self)
annotator/uniformer/mmcv/parallel/data_container.py:76
Functionparse_version_info
Parse a version string into a tuple. Args: version_str (str): The version string. length (int): The maximum number of version lev
annotator/uniformer/mmcv/version.py:5
Functionpixel_group
Group pixels into text instances, which is widely used text detection methods. Arguments: score (np.array or Tensor): The foreground
annotator/uniformer/mmcv/ops/pixel_group.py:10
Functionpoints_in_boxes_all
Find all boxes in which each point is (CUDA). Args: points (torch.Tensor): [B, M, 3], [x, y, z] in LiDAR/DEPTH coordinate boxes (
annotator/uniformer/mmcv/ops/points_in_boxes.py:95
Functionpoints_in_boxes_cpu
Find all boxes in which each point is (CPU). The CPU version of :meth:`points_in_boxes_all`. Args: points (torch.Tensor): [B, M, 3],
annotator/uniformer/mmcv/ops/points_in_boxes.py:58
Functionpoints_in_boxes_part
Find the box in which each point is (CUDA). Args: points (torch.Tensor): [B, M, 3], [x, y, z] in LiDAR/DEPTH coordinate boxes (to
annotator/uniformer/mmcv/ops/points_in_boxes.py:11
Functionpool_flops_counter_hook
(module, input, output)
annotator/uniformer/mmcv/cnn/utils/flops_counter.py:425
Functionpose_gallery_callback
(evt: gr.SelectData)
app_pose.py:77
Methodposition
int: Current cursor position, indicating frame decoded.
annotator/uniformer/mmcv/video/io.py:120
Functionpost_process_gif
(list_of_results, image_resolution)
utils.py:174
Functionposterize
Posterize an image (reduce the number of bits for each color channel) Args: img (ndarray): Image to be posterized. bits (int): Nu
annotator/uniformer/mmcv/image/photometric.py:85
Functionpre_process_canny
(input_video, low_threshold=100, high_threshold=200)
utils.py:47
Functionpre_process_depth
(input_video, apply_depth_detect: bool = True)
utils.py:59
Functionpre_process_pose
(input_video, apply_pose_detect: bool = True)
utils.py:77
Functionprepare_video
(video_path:str, resolution:int, device, dtype, normalize=True, start_t:float=0, end_t:float=-1, output_fps:in
utils.py:136
Methodpretty_text
(self)
annotator/uniformer/mmcv/utils/config.py:407
Methodprocess_controlnet_canny
(self, video_path, prompt,
model.py:133
Methodprocess_controlnet_canny_db
(self, db_path, video_path,
model.py:323
Methodprocess_controlnet_depth
(self, video_path, prompt,
model.py:198
Methodprocess_controlnet_pose
(self, video_path, prompt,
model.py:261
Methodprocess_pix2pix
(self, video, prompt, resolution=512,
model.py:389
Methodprocess_text2video
(self, prompt, model_name="dreamlike-art/dreamlike-photo
model.py:427
Methodput
Write data to a given ``filepath`` with 'wb' mode. Note: ``put`` will create a directory if the directory of ``filepath``
annotator/uniformer/mmcv/fileio/file_client.py:538
Methodput_text
Save data to a given ``filepath``. Args: obj (str): Data to be written. filepath (str or Path): Path to write data.
annotator/uniformer/mmcv/fileio/file_client.py:190
Methodput_text
Write data to a given ``filepath`` with 'w' mode. Note: ``put_text`` will create a directory if the directory of ``fi
annotator/uniformer/mmcv/fileio/file_client.py:553
Methodrank
int: Rank of current process. (distributed training)
annotator/uniformer/mmcv/runner/base_runner.py:144
Functionread_image
Read image and output RGB image (0-1). Args: path (str): path to file Returns: array: RGB image (0-1)
annotator/midas/utils.py:97
Functionread_pfm
Read pfm file. Args: path (str): path to file Returns: tuple: (data, scale)
annotator/midas/utils.py:9
Methodregister_backend
Register a backend to FileClient. This method can be used as a normal class method or a decorator. .. code-block:: python
annotator/uniformer/mmcv/fileio/file_client.py:922
Functionregister_handler
(file_formats, **kwargs)
annotator/uniformer/mmcv/fileio/io.py:145
Methodregister_profiler_hook
(self, profiler_config)
annotator/uniformer/mmcv/runner/base_runner.py:493
Methodregister_scheme
Register a loader to CheckpointLoader. This method can be used as a normal class method or a decorator. Args: prefixes (
annotator/uniformer/mmcv/runner/checkpoint.py:185
Methodregister_training_hooks
Register default hooks for iter-based training. Checkpoint hook, optimizer stepper hook and logger hooks will be set to `by_epoch=Fal
annotator/uniformer/mmcv/runner/iter_based_runner.py:224
Functionrelu_flops_counter_hook
(module, input, output)
annotator/uniformer/mmcv/cnn/utils/flops_counter.py:413
Methodremove
Remove a file. Args: filepath (str or Path): Path to be removed.
annotator/uniformer/mmcv/fileio/file_client.py:204
Methodremove
Remove a file. Args: filepath (str or Path): Path to be removed.
annotator/uniformer/mmcv/fileio/file_client.py:573
Functionremove_flops_counter_hook_function
(module)
annotator/uniformer/mmcv/cnn/utils/flops_counter.py:546
Functionrequires_executable
A decorator to check if some executable files are installed. Example: >>> @requires_executable('ffmpeg') >>> func(arg1, args):
annotator/uniformer/mmcv/utils/misc.py:276
Functionrequires_package
A decorator to check if some python packages are installed. Example: >>> @requires_package('numpy') >>> func(arg1, args):
annotator/uniformer/mmcv/utils/misc.py:260
Methodreset_classifier
(self, num_classes, global_pool='')
annotator/uniformer/mmseg/models/backbones/uniformer.py:379
Functionreset_flops_count
Reset statistics computed so far. A method to Reset computed statistics, which will be available after `add_flops_counting_methods()` is call
annotator/uniformer/mmcv/cnn/utils/flops_counter.py:389
Functionresize_depth
Resize depth map and bring to CPU (numpy). Args: depth (tensor): depth width (int): image width height (int): image heigh
annotator/midas/utils.py:146
Functionresize_image
(input_image, resolution)
annotator/util.py:28
Functionresize_image
Resize image and make it fit for network. Args: img (array): image Returns: tensor: data ready for network
annotator/midas/utils.py:116
Functionresize_video
Resize a video. Args: in_file (str): Input video filename. out_file (str): Output video filename. size (tuple): Expected
annotator/uniformer/mmcv/video/processing.py:55
Methodresolution
tuple: Video resolution (width, height).
annotator/uniformer/mmcv/video/io.py:100
Methodresume
Resume model from checkpoint. Args: checkpoint (str): Checkpoint to resume from. resume_optimizer (bool, optional): W
annotator/uniformer/mmcv/runner/iter_based_runner.py:140
Functionrevert_sync_batchnorm
Helper function to convert all `SyncBatchNorm` (SyncBN) and `mmcv.ops.sync_bn.SyncBatchNorm`(MMSyncBN) layers in the model to `BatchNormXd` la
annotator/uniformer/mmcv/cnn/utils/sync_bn.py:21
Functionrgb2gray
Convert a RGB image to grayscale image. Args: img (ndarray): The input image. keepdim (bool): If False (by default), then return
annotator/uniformer/mmcv/image/colorspace.py:39
Functionrgb2ycbcr
Convert a RGB image to YCbCr image. This function produces the same results as Matlab's `rgb2ycbcr` function. It implements the ITU-R BT.601
annotator/uniformer/mmcv/image/colorspace.py:143
Methodrun
Start running. Args: data_loaders (list[:obj:`DataLoader`]): Dataloaders for training and validation.
annotator/uniformer/mmcv/runner/epoch_based_runner.py:72
Methodrun
Start running. Args: data_loaders (list[:obj:`DataLoader`]): Dataloaders for training and validation.
annotator/uniformer/mmcv/runner/iter_based_runner.py:87
Methodsample
Placeholder for sample function.
annotator/uniformer/mmseg/core/seg/sampler/base_pixel_sampler.py:11
Functionsave_checkpoint
Save checkpoint to file. The checkpoint will have 3 fields: ``meta``, ``state_dict`` and ``optimizer``. By default ``meta`` will contain vers
annotator/uniformer/mmcv_custom/checkpoint.py:438
Methodsave_checkpoint
Save the checkpoint. Args: out_dir (str): The directory that checkpoints are saved. filename_tmpl (str, optional): Th
annotator/uniformer/mmcv/runner/epoch_based_runner.py:132
Methodsave_checkpoint
Save checkpoint to file. Args: out_dir (str): Directory to save checkpoint files. filename_tmpl (str, optional): Chec
annotator/uniformer/mmcv/runner/iter_based_runner.py:179
← previousnext →1,601–1,700 of 1,788, ranked by callers