Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/cangcz/AnchorCrafter
/ functions
Functions
139 in github.com/cangcz/AnchorCrafter
⨍
Functions
139
◇
Types & classes
25
Method
__len__
(self)
anchor_dataset.py:299
Function
_add_variant
(weights_name: str, variant: Optional[str] = None)
anchor_crafter/modules/pose_hand_net.py:13
Function
_add_variant
(weights_name: str, variant: Optional[str] = None)
anchor_crafter/modules/track_net.py:13
Method
_set_gradient_checkpointing
(self, module, value=False)
anchor_crafter/modules/unet.py:330
Method
attn_processors
r""" Returns: `dict` of attention processors: A dictionary containing all attention processors used in the model with
anchor_crafter/modules/unet.py:255
Method
do_classifier_free_guidance
(self)
anchor_crafter/pipelines/pipeline.py:353
Function
download_image
(url)
train.py:548
Function
draw_bodypose
(canvas, candidate, subset)
evalution/preprocess/src/util.py:42
Function
draw_handpose
(canvas, all_hand_peaks, show_number=False)
evalution/preprocess/src/util.py:77
Function
draw_handpose_by_opencv
(canvas, peaks, show_number=False)
evalution/preprocess/src/util.py:108
Method
enable_forward_chunking
Sets the attention processor to use [feed forward chunking](https://huggingface.co/blog/reformer#2-chunked-feed-forward-layers).
anchor_crafter/modules/unet.py:335
Function
export_to_gif
Export a list of frames to a GIF. Args: - frames (list): List of frames (as numpy arrays or PIL Image objects). - output_gif_path (s
train.py:250
Function
export_to_video
(video_frames, output_video_path, fps)
train.py:240
Method
fn_recursive_add_processors
( name: str, module: torch.nn.Module, processors: Dict[str, At
anchor_crafter/modules/unet.py:264
Method
fn_recursive_attn_processor
(name: str, module: torch.nn.Module, processor)
anchor_crafter/modules/unet.py:303
Method
fn_recursive_feed_forward
(module: torch.nn.Module, chunk_size: int, dim: int)
anchor_crafter/modules/unet.py:354
Function
forward
(self, hidden_states)
anchor_crafter/utils/geglu_patch.py:6
Method
forward
(self, pose_features, inp_noisy_latents, conditional_latents, timesteps, encoder_hidden_states
train.py:64
Method
forward
( self, attn, hidden_states, encoder_hidden_states=None, attention_mas
anchor_crafter/modules/attention_processor.py:30
Method
forward
( self, attn, hidden_states, encoder_hidden_states=None, attention_mas
anchor_crafter/modules/attention_processor.py:116
Method
forward
( self, attn, hidden_states, encoder_hidden_states=None, attention_mas
anchor_crafter/modules/attention_processor.py:245
Method
forward
( self, attn, hidden_states, encoder_hidden_states=None, attention_mas
anchor_crafter/modules/attention_processor.py:347
Method
forward
r""" The [`UNetSpatioTemporalConditionModel`] forward method. Args: sample (`torch.FloatTensor`): The noi
anchor_crafter/modules/unet.py:364
Method
forward
(self, x)
anchor_crafter/modules/pose_hand_net.py:72
Method
forward
(self, x)
anchor_crafter/modules/track_net.py:72
Method
forward
The [`TransformerTemporal`] forward method. Args: hidden_states (`torch.LongTensor` of shape `(batch size, num latent pi
anchor_crafter/modules/attention.py:107
Method
forward
Args: hidden_states (`torch.FloatTensor` of shape `(batch size, channel, height, width)`): Input hidden_states.
anchor_crafter/modules/attention.py:263
Method
forward
(self, embeds)
anchor_crafter/modules/obj_proj_net.py:19
Method
forward
(self, embeds)
anchor_crafter/modules/obj_attn_net.py:33
Method
forward
(self, x)
evalution/preprocess/src/model.py:114
Method
forward
(self, x)
evalution/preprocess/src/model.py:204
Method
guidance_scale
(self)
anchor_crafter/pipelines/pipeline.py:346
Function
handDetect
(candidate, subset, oriImg)
evalution/preprocess/src/util.py:128
Function
npmax
(array)
evalution/preprocess/src/util.py:193
Method
num_timesteps
(self)
anchor_crafter/pipelines/pipeline.py:359
Function
padRightDownCorner
(img, stride, padValue)
evalution/preprocess/src/util.py:12
Method
release_memory
(self)
anchor_crafter/dwpose/dwpose_detector.py:28
Method
set_default_attn_processor
Disables custom attention processors and sets the default attention implementation.
anchor_crafter/modules/unet.py:316
Function
transfer
(model, model_weights)
evalution/preprocess/src/util.py:35
← previous
101–139 of 139, ranked by callers