MCPcopy Create free account

hub / github.com/Francis-Rings/StableAnimator / functions

Functions480 in github.com/Francis-Rings/StableAnimator

⨍ Functions 480◇ Types & classes 92
↓ 1 callersFunctioncalculate_val
(thresholds, embeddings1, embeddings2, actual_issame,
animation/helper/eval/verification.py:124
↓ 1 callersMethodcheck_batch
(self, img)
animation/helper/onnx_helper.py:184
↓ 1 callersMethodcheck_inputs
(self, image, height, width)
animation/pipelines/inference_pipeline_animation.py:280
↓ 1 callersMethodcheck_inputs
(self, image, height, width)
animation/pipelines/pipeline_animation.py:301
↓ 1 callersMethodcheck_inputs
(self, image, height, width)
animation/pipelines/validation_pipeline_animation.py:308
↓ 1 callersMethodcheck_inputs
(self, image, height, width)
animation/pipelines/inference_pipeline_animation_pro.py:283
↓ 1 callersFunctionconv1x1
1x1 convolution
animation/helper/backbones/iresnet.py:20
↓ 1 callersFunctionconv1x1
1x1 convolution
animation/helper/backbones/iresnet2060.py:22
↓ 1 callersFunctionconvert_onnx
(net, path_module, output, opset=11, simplify=False)
animation/helper/torch2onnx.py:6
↓ 1 callersFunctioncreate_image_grid
(images, rows, cols, target_size=(256, 256))
train.py:80
↓ 1 callersFunctioncreate_image_grid
(images, rows, cols, target_size=(256, 256))
train_single.py:82
↓ 1 callersFunctiondali_data_iter
Parameters: ---------- initial_fill: int Size of the buffer that is used for shuffling. If random_shuffle is False, this paramete
animation/helper/dataset.py:193
↓ 1 callersFunctiondali_random_gaussian_blur
(img, window_size)
animation/helper/dataset.py:219
↓ 1 callersFunctiondali_random_gray
(img, prob_gray)
animation/helper/dataset.py:222
↓ 1 callersFunctiondali_random_hsv
(img, hue, saturation)
animation/helper/dataset.py:227
↓ 1 callersFunctiondali_random_resize
(img, resize_size, image_size=112)
animation/helper/dataset.py:215
↓ 1 callersFunctiondecode
Modulate simcc distribution with Gaussian. Args: simcc_x (np.ndarray[K, Wx]): model predicted simcc in x. simcc_y (np.ndarray[K,
DWPose/dwpose_utils/onnxpose.py:333
↓ 1 callersFunctiondecode_latents
( vae, latents, num_frames, decode_chunk_size=8)
animation/utils/utils.py:14
↓ 1 callersMethoddecode_latents
( self, latents: torch.Tensor, num_frames: int, decode_chu
animation/pipelines/inference_pipeline_animation.py:247
↓ 1 callersMethoddecode_latents
( self, latents: torch.Tensor, num_frames: int, decode_chunk_size: int = 8)
animation/pipelines/pipeline_animation.py:268
↓ 1 callersMethoddecode_latents
( self, latents: torch.Tensor, num_frames: int, decode_chu
animation/pipelines/validation_pipeline_animation.py:275
↓ 1 callersMethoddecode_latents
( self, latents: torch.Tensor, num_frames: int, decode_chu
animation/pipelines/inference_pipeline_animation_pro.py:250
↓ 1 callersFunctiondecode_latents_scheduler_new
(latents, num_frames, decode_chunk_size=8, vae=None, device=None)
animation/pipelines/euler_discrete_pro.py:92
↓ 1 callersFunctiondemo_postprocess
(outputs, img_size, p6=False)
DWPose/dwpose_utils/onnxdet.py:58
↓ 1 callersFunctiondraw_bodypose
(canvas, candidate, subset, score)
DWPose/skeleton_extraction.py:16
↓ 1 callersFunctiondraw_bodypose_aligned
(canvas, candidate, subset, score)
DWPose/training_skeleton_extraction.py:19
↓ 1 callersFunctiondraw_facepose
(canvas, all_lmks, all_scores)
DWPose/skeleton_extraction.py:90
↓ 1 callersFunctiondraw_facepose_aligned
(canvas, all_lmks, all_scores)
DWPose/training_skeleton_extraction.py:89
↓ 1 callersFunctiondraw_handpose
(canvas, all_hand_peaks, all_hand_scores)
DWPose/skeleton_extraction.py:61
↓ 1 callersFunctiondraw_handpose_aligned
(canvas, all_hand_peaks, all_hand_scores)
DWPose/training_skeleton_extraction.py:60
↓ 1 callersFunctiondraw_pose_aligned
(pose, H, W, ref_w=2160)
DWPose/training_skeleton_extraction.py:101
↓ 1 callersFunctionencode_image
(pixel_values)
train.py:1213
↓ 1 callersFunctionencode_image
(pixel_values)
train_single.py:1201
↓ 1 callersFunctionevaluate
(embeddings, actual_issame, nrof_folds=10, pca=0)
animation/helper/eval/verification.py:179
↓ 1 callersFunctionexport_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_pa
train.py:346
↓ 1 callersFunctionexport_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_pa
inference_op.py:44
↓ 1 callersFunctionexport_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_pa
train_single.py:350
↓ 1 callersFunctionexport_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_pa
inference_basic.py:58
↓ 1 callersFunctionexport_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_pa
app.py:65
↓ 1 callersFunctionextract
(model_root, dataset)
animation/helper/onnx_ijbc.py:56
↓ 1 callersMethodfind_frames_list
(self, frames_path)
animation/dataset/animation_dataset.py:49
↓ 1 callersMethodforward
(self, x)
animation/helper/backbones/vit.py:16
↓ 1 callersMethodforward_features
(self, x)
animation/helper/backbones/vit.py:253
↓ 1 callersMethodforward_impl
(self, x)
animation/helper/backbones/iresnet.py:47
↓ 1 callersMethodframe_count
(self, frames_path)
animation/dataset/animation_dataset.py:43
↓ 1 callersFunctionget_config
(config_file)
animation/helper/utils/utils_config.py:5
↓ 1 callersFunctionget_dataloader
( root_dir, local_rank, batch_size, dali = False, dali_aug = False, seed = 2048, n
animation/helper/dataset.py:19
↓ 1 callersFunctionget_down_block
( down_block_type: str, num_layers: int, in_channels: int, out_channels: int, temb_ch
animation/modules/unet_3d_blocks.py:85
↓ 1 callersFunctionget_face_masks
(image_path, save_path, app, face_helper, height=904, width=512)
face_mask_extraction.py:10
↓ 1 callersFunctionget_image_feature
(img_path, files_list, model_path, epoch, gpu_id)
animation/helper/eval_ijbc.py:154
↓ 1 callersFunctionget_image_pose
(ref_image_path)
DWPose/training_skeleton_extraction.py:117
↓ 1 callersFunctionget_mbf
(fp16, num_features, blocks=(1, 4, 6, 2), scale=2)
animation/helper/backbones/mobilefacenet.py:143
↓ 1 callersFunctionget_mbf_large
(fp16, num_features, blocks=(2, 8, 12, 4), scale=4)
animation/helper/backbones/mobilefacenet.py:146
↓ 1 callersMethodget_prepare_faceid
(self, face_image)
animation/pipelines/pipeline_animation.py:135
↓ 1 callersFunctionget_simcc_maximum
Get maximum response location and value from simcc representations. Note: instance number: N num_keypoints: K heatmap hei
DWPose/dwpose_utils/onnxpose.py:288
↓ 1 callersFunctionget_up_block
( up_block_type: str, num_layers: int, in_channels: int, out_channels: int, prev_outp
animation/modules/unet_3d_blocks.py:177
↓ 1 callersFunctionget_video_pose
(video_path, ref_image_path, poses_folder_path=None)
DWPose/skeleton_extraction.py:137
↓ 1 callersFunctionget_warp_matrix
Calculate the affine transformation matrix that can warp the bbox area in the input image to the output size. Args: center (np.ndarra
DWPose/dwpose_utils/onnxpose.py:201
↓ 1 callersFunctionimage2template_feature
(img_feats=None, templates=None, medias=None)
animation/helper/eval_ijbc.py:212
↓ 1 callersFunctionimage2template_feature
(img_feats=None, templates=None, medias=None)
animation/helper/onnx_ijbc.py:100
↓ 1 callersFunctioninference
(weight, name, img)
animation/helper/inference.py:11
↓ 1 callersFunctioninference
Inference RTMPose model. Args: sess (ort.InferenceSession): ONNXRuntime session. img (np.ndarray): Input image in shape. Ret
DWPose/dwpose_utils/onnxpose.py:52
↓ 1 callersFunctioninference_detector
(session, oriImg)
DWPose/dwpose_utils/onnxdet.py:98
↓ 1 callersFunctioninference_pose
(session, out_bbox, oriImg)
DWPose/dwpose_utils/onnxpose.py:353
↓ 1 callersMethodinit_dataset
(self, val_targets, data_dir, image_size)
animation/helper/utils/utils_callbacks.py:53
↓ 1 callersMethodinit_face_model
(self, app = None, face_helper = None, handler_ante = None, face_embedding_extractor = None)
animation/pipelines/euler_discrete_pro.py:331
↓ 1 callersFunctioninit_logging
(rank, models_root)
animation/helper/utils/utils_logging.py:30
↓ 1 callersFunctioniresnet100
(pretrained=False, progress=True, **kwargs)
animation/helper/backbones/iresnet.py:187
↓ 1 callersFunctioniresnet18
(pretrained=False, progress=True, **kwargs)
animation/helper/backbones/iresnet.py:172
↓ 1 callersFunctioniresnet200
(pretrained=False, progress=True, **kwargs)
animation/helper/backbones/iresnet.py:192
↓ 1 callersFunctioniresnet2060
(pretrained=False, progress=True, **kwargs)
animation/helper/backbones/iresnet2060.py:175
↓ 1 callersFunctioniresnet34
(pretrained=False, progress=True, **kwargs)
animation/helper/backbones/iresnet.py:177
↓ 1 callersFunctioniresnet50
(pretrained=False, progress=True, **kwargs)
animation/helper/backbones/iresnet.py:182
↓ 1 callersFunctionload_images_from_folder
(folder, width, height)
inference_op.py:32
↓ 1 callersFunctionload_images_from_folder
(folder, width, height)
inference_basic.py:27
↓ 1 callersFunctionload_images_from_folder
(folder, width, height)
app.py:32
↓ 1 callersFunctionlog_validation
( vae, image_encoder, unet, pose_net, face_encoder, app,
train.py:1579
↓ 1 callersFunctionlog_validation
( vae, image_encoder, unet, pose_net, face_encoder, app,
train_single.py:1553
↓ 1 callersFunctionlogsnr_schedule_cosine
(t, logsnr_min, logsnr_max)
train.py:187
↓ 1 callersFunctionlogsnr_schedule_cosine
(t, logsnr_min, logsnr_max)
train_single.py:189
↓ 1 callersFunctionlogsnr_schedule_cosine_interpolated
(t, image_d, noise_d_low, noise_d_high, logsnr_min, logsnr_max)
train.py:196
↓ 1 callersFunctionlogsnr_schedule_cosine_interpolated
(t, image_d, noise_d_low, noise_d_high, logsnr_min, logsnr_max)
train_single.py:198
↓ 1 callersFunctionmain
()
train.py:842
↓ 1 callersFunctionmain
()
train_single.py:853
↓ 1 callersFunctionmain
(args)
animation/helper/onnx_ijbc.py:170
↓ 1 callersFunctionmain
(args)
animation/helper/train_v2.py:42
↓ 1 callersFunctionmain
(args)
animation/helper/scripts/shuffle_rec.py:68
↓ 1 callersFunctionmulticlass_nms
Multiclass NMS implemented in Numpy. Class-aware version.
DWPose/dwpose_utils/onnxdet.py:35
↓ 1 callersMethodnext
(self)
animation/helper/dataset.py:94
↓ 1 callersFunctionnms
Single class NMS implemented in Numpy.
DWPose/dwpose_utils/onnxdet.py:6
↓ 1 callersFunctionparse_args
()
train.py:383
↓ 1 callersFunctionparse_args
()
inference_op.py:65
↓ 1 callersFunctionparse_args
()
train_single.py:387
↓ 1 callersFunctionparse_args
()
inference_basic.py:79
↓ 1 callersFunctionpostprocess
Postprocess for RTMPose model output. Args: outputs (np.ndarray): Output of RTMPose model. model_input_size (tuple): RTMPose mode
DWPose/dwpose_utils/onnxpose.py:80
↓ 1 callersFunctionpostprocess_scheduler
(image: torch.Tensor)
animation/pipelines/euler_discrete_pro.py:23
↓ 1 callersMethodprepare_extra_step_kwargs
(self, generator, eta)
animation/pipelines/inference_pipeline_animation.py:345
↓ 1 callersMethodprepare_extra_step_kwargs
(self, generator, eta)
animation/pipelines/pipeline_animation.py:366
↓ 1 callersMethodprepare_extra_step_kwargs
(self, generator, eta)
animation/pipelines/validation_pipeline_animation.py:373
↓ 1 callersMethodprepare_extra_step_kwargs
(self, generator, eta)
animation/pipelines/inference_pipeline_animation_pro.py:348
← previousnext →101–200 of 480, ranked by callers