MCPcopy Create free account

hub / github.com/Ground-A-Video/Ground-A-Video / functions

Functions1,051 in github.com/Ground-A-Video/Ground-A-Video

⨍ Functions 1,051◇ Types & classes 244
↓ 1 callersFunctioninfer_optical_flow
(model, frameA, frameB, height=512, width=512, device='cuda', save_dir=None, i=0)
controlnet/utils.py:40
↓ 1 callersMethodinfer_with_flip_aug
Inference interface for the model with horizontal flip augmentation Horizontal flip augmentation improves the accuracy of the model b
annotator/zoe/zoedepth/models/depth_model.py:99
↓ 1 callersMethodinit_
(self)
ldm/modules/x_transformer.py:31
↓ 1 callersMethodinit_
(self)
ldm/modules/x_transformer.py:595
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list(), only_model=False)
ldm/models/diffusion/classifier.py:70
↓ 1 callersMethodinit_optimizer
(self)
annotator/zoe/zoedepth/trainers/base_trainer.py:95
↓ 1 callersMethodinit_prompt
( self, prompt: str, batch_size, text_encoder)
null_inv.py:109
↓ 1 callersMethodinit_scheduler
(self)
annotator/zoe/zoedepth/trainers/base_trainer.py:113
↓ 1 callersMethodinstantiate_pretrained
(self, config)
ldm/modules/diffusionmodules/model.py:807
↓ 1 callersMethodinvert
( self, latents: torch.Tensor, prompt: str, grounding_input=None, in
null_inv.py:188
↓ 1 callersFunctionis_image_file
(filename)
ldm/modules/image_degradation/utils_image.py:29
↓ 1 callersFunctionismap
(x)
ldm/util.py:34
↓ 1 callersMethodkl
(self, other=None)
ldm/modules/distributions/distributions.py:39
↓ 1 callersMethodload_2d_state_dict
(self, state_dict, **kwargs)
controlnet/unet_3d_condition.py:464
↓ 1 callersFunctionload_ckpt
(ckpt_path)
inference.py:250
↓ 1 callersMethodload_classifier
(self, ckpt_path, pool)
ldm/models/diffusion/classifier.py:95
↓ 1 callersMethodload_diffusion
(self)
ldm/models/diffusion/classifier.py:88
↓ 1 callersFunctionload_meta_from_yaml
(file_path)
main.py:7
↓ 1 callersFunctionload_model
Load the specified network. Args: device (device): the torch device used model_path (str): path to saved model model_type
annotator/zoe/zoedepth/models/base_models/midas_repo/midas/model_loader.py:29
↓ 1 callersFunctionload_unet2d
(pretrained_unet_path)
inference.py:277
↓ 1 callersFunctionload_unet3d
(pretrained_unet_path)
inference.py:265
↓ 1 callersFunctionlog_binom
log(nCk) using stirling approximation
annotator/zoe/zoedepth/models/layers/dist_layers.py:29
↓ 1 callersFunctionlog_txt_as_img
(wh, xc, size=10)
ldm/util.py:10
↓ 1 callersFunctionmain
(args)
annotator/zoe/zoedepth/models/base_models/midas_repo/ros/midas_cpp/scripts/listener_original.py:51
↓ 1 callersFunctionmain
(args)
annotator/zoe/zoedepth/models/base_models/midas_repo/ros/midas_cpp/scripts/listener.py:51
↓ 1 callersFunctionmake_beta_schedule
(schedule, n_timestep, linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3)
ldm/modules/diffusionmodules/util.py:30
↓ 1 callersFunctionmake_ddim_sampling_parameters
(alphacums, ddim_timesteps, eta, verbose=True)
ldm/modules/diffusionmodules/util.py:72
↓ 1 callersFunctionmake_ddim_timesteps
(ddim_discr_method, num_ddim_timesteps, num_ddpm_timesteps, verbose=True)
ldm/modules/diffusionmodules/util.py:55
↓ 1 callersMethodmake_schedule
(self, ddim_num_steps, ddim_discretize="uniform", ddim_eta=0.)
ldm/models/diffusion/ddim.py:29
↓ 1 callersFunctionmax_neg_value
(tensor)
ldm/modules/x_transformer.py:82
↓ 1 callersFunctionmeasure_perplexity
(predicted_indices, n_embed)
ldm/modules/losses/vqperceptual.py:26
↓ 1 callersMethodmode
(self)
ldm/modules/distributions/distributions.py:20
↓ 1 callersFunctionmodify_file
()
annotator/zoe/zoedepth/models/base_models/midas_repo/tf/make_onnx_model.py:18
↓ 1 callersFunctionnot_equals
(val)
ldm/modules/x_transformer.py:70
↓ 1 callersMethodnull_optimization
( self, latents, null_inner_steps, epsilon, null_base_lr=1e-2,
null_inv.py:145
↓ 1 callersFunctionnum_value_pixels
(arr)
annotator/zoe/zoedepth/data/preprocess.py:44
↓ 1 callersMethodp_sample_ddim
(self, input, index, uc=None, uncond_embeddings=None, guidance_scale=1)
ldm/models/diffusion/ddim.py:122
↓ 1 callersMethodparse_img_size
(config)
annotator/zoe/zoedepth/models/base_models/midas.py:356
↓ 1 callersFunctionparse_list
Parse a list of values for the key if the value is a string. The values are separated by a comma. Modifies the config in place.
annotator/zoe/zoedepth/utils/config.py:295
↓ 1 callersFunctionpatches_from_image
(img, p_size=512, p_overlap=64, p_max=800)
ldm/modules/image_degradation/utils_image.py:93
↓ 1 callersMethodpositional_encoding_1d
Generate positional encodings Args: sequence_length (int): Sequence length embedding_dim (int): Embedding dimension
annotator/zoe/zoedepth/models/layers/patch_transformer.py:50
↓ 1 callersMethodpostprocess
(self, sample)
annotator/zoe/zoedepth/data/data_mono.py:289
↓ 1 callersFunctionprepare_batch
(meta, batch=1, max_objs=30, ith_clip=None, model=None, processor=None)
inference.py:187
↓ 1 callersFunctionprepare_cond
( images, device, dtype, width=512, height=512, batch_size=1, num_images_per_prompt=1, do_classifier_free_
controlnet/utils.py:120
↓ 1 callersFunctionprepare_depth
(input_images, device, dtype, save_dir=None)
controlnet/utils.py:89
↓ 1 callersFunctionprepare_image
( image, width, height, batch_size, num_images_per_prompt, device, dtype, do_classifier_free_guidance )
controlnet/utils.py:136
↓ 1 callersFunctionprepare_magnitude_map
(optical_flows, save_dir=None)
controlnet/utils.py:20
↓ 1 callersFunctionprepare_optical_flow
(input_image_path, device, save_dir=None)
controlnet/utils.py:73
↓ 1 callersFunctionpreprocess
(img1_batch, img2_batch)
controlnet/utils.py:54
↓ 1 callersMethodpreprocess
(self, x)
ldm/modules/encoders/modules_backup.py:216
↓ 1 callersMethodpreprocess
(self, x)
ldm/modules/encoders/modules.py:227
↓ 1 callersFunctionproject
x (Batch*768) should be the penultimate feature of CLIP (before projection) projection_matrix (768*768) is the CLIP projection matrix, which
inference.py:71
↓ 1 callersMethodraise_if_nan
(self, losses)
annotator/zoe/zoedepth/trainers/base_trainer.py:125
↓ 1 callersFunctionrandom_crop
(lq, hq, sf=4, lq_patchsize=64)
ldm/modules/image_degradation/bsrgan_light.py:431
↓ 1 callersMethodrandom_crop
(self, img, depth, height, width)
annotator/zoe/zoedepth/data/data_mono.py:444
↓ 1 callersMethodrandom_translate
(self, img, depth, max_t=20)
annotator/zoe/zoedepth/data/data_mono.py:456
↓ 1 callersFunctionrecurse
(inp)
annotator/zoe/zoedepth/utils/config.py:258
↓ 1 callersMethodregister_schedule
(self, beta_schedule="linear", timesteps=1000, linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3)
ldm/models/diffusion/ddpm.py:19
↓ 1 callersFunctionrepetitive_roundrobin
cycles through iterables but sample wise first yield first sample from first iterable then first sample from second iterable and so on th
annotator/zoe/zoedepth/data/data_mono.py:181
↓ 1 callersMethodreset_noise_accs
(self)
ldm/models/diffusion/classifier.py:202
↓ 1 callersMethodreshape_batch_dim_to_heads
(self,tensor)
controlnet/attention.py:373
↓ 1 callersMethodreshape_batch_dim_to_heads
(self,tensor)
controlnet/attention.py:449
↓ 1 callersMethodreshape_batch_dim_to_heads
(self,tensor)
ldm/modules/attention.py:210
↓ 1 callersMethodreshape_batch_dim_to_heads
(self,tensor)
ldm/modules/attention.py:291
↓ 1 callersFunctionrestore_file
()
annotator/zoe/zoedepth/models/base_models/midas_repo/tf/make_onnx_model.py:32
↓ 1 callersMethodrestore_first_conv_from_SD
(self)
ldm/modules/diffusionmodules/openaimodel.py:400
↓ 1 callersFunctionrun
(meta, config, starting_noise=None)
inference.py:289
↓ 1 callersFunctionrun
Run MonoDepthNN to compute depth maps. Args: input_path (str): path to input folder output_path (str): path to output folder
annotator/zoe/zoedepth/models/base_models/midas_repo/run.py:105
↓ 1 callersFunctionrun
Run MonoDepthNN to compute depth maps. Args: input_path (str): path to input folder output_path (str): path to output folder
annotator/zoe/zoedepth/models/base_models/midas_repo/tf/run_pb.py:13
↓ 1 callersFunctionrun
Run MonoDepthNN to compute depth maps. Args: model_path (str): path to saved model
annotator/zoe/zoedepth/models/base_models/midas_repo/tf/make_onnx_model.py:64
↓ 1 callersFunctionrun
Run MonoDepthNN to compute depth maps. Args: input_path (str): path to input folder output_path (str): path to output folder
annotator/zoe/zoedepth/models/base_models/midas_repo/tf/run_onnx.py:17
↓ 1 callersMethodsample
(self)
ldm/modules/distributions/distributions.py:35
↓ 1 callersMethodsample
(self, S, shape, input, uc=None, uncond_embeddings=None, guidance_scale=1, mask=None, x0=None)
ldm/models/diffusion/ddim.py:62
↓ 1 callersFunctionsave_images_as_gif
(images, save_path, optimize=False, loop=0, duration=250)
inference.py:239
↓ 1 callersMethodschedule
(self, n, **kwargs)
ldm/lr_scheduler.py:17
↓ 1 callersMethodschedule
(self, n, **kwargs)
ldm/lr_scheduler.py:59
↓ 1 callersMethodset_attention_slice
r""" Enable sliced attention computation. When this option is enabled, the attention module will split the input tensor in slices, to
controlnet/unet_3d_condition.py:209
↓ 1 callersMethodset_attention_slice
r""" Enable sliced attention computation. When this option is enabled, the attention module will split the input tensor in slices, to
controlnet/controlnet.py:357
↓ 1 callersMethodset_attention_slice
r""" Enable sliced attention computation. When this option is enabled, the attention module will split the input tensor in slices, to
controlnet/controlnet_3d.py:331
↓ 1 callersMethodset_fetch_features
(self, fetch_features)
annotator/zoe/zoedepth/models/base_models/midas.py:232
↓ 1 callersMethodset_output_channels
(self, model_type)
annotator/zoe/zoedepth/models/base_models/midas.py:330
↓ 1 callersMethodset_trainable
(self, trainable)
annotator/zoe/zoedepth/models/base_models/midas.py:224
↓ 1 callersFunctionsplit_combined_args
Splits the arguments that are combined with '__' into multiple arguments. Combined arguments should have equal number of keys and values.
annotator/zoe/zoedepth/utils/config.py:271
↓ 1 callersFunctionstem_b4_transpose
Modification of https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/levit.py: stem_b16 such that ConvTranspose2
annotator/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/levit.py:86
↓ 1 callersFunctionsynset2idx
(path_to_yaml="ldm/data/index_synset.yaml")
ldm/data/imagenet.py:20
↓ 1 callersFunctiontalker
()
annotator/zoe/zoedepth/models/base_models/midas_repo/ros/midas_cpp/scripts/talker.py:14
↓ 1 callersMethodtrain_on_batch
(self, batch, train_step)
annotator/zoe/zoedepth/trainers/base_trainer.py:119
↓ 1 callersMethodtrain_preprocess
(self, image, depth_gt)
annotator/zoe/zoedepth/data/data_mono.py:473
↓ 1 callersFunctiontransforms
()
annotator/zoe/zoedepth/models/base_models/midas_repo/hubconf.py:303
↓ 1 callersMethodupdate
(self, e=None, **f)
annotator/zoe/zoedepth/utils/easydict/__init__.py:145
↓ 1 callersFunctionupsample_2d
r"""Upsample2D a batch of 2D images with the given filter. Accepts a batch of 2D images of the shape `[N, C, H, W]` or `[N, H, W, C]` and upsample
controlnet/resnet.py:357
↓ 1 callersMethodvalidate_on_batch
(self, batch, val_step)
annotator/zoe/zoedepth/trainers/base_trainer.py:122
↓ 1 callersMethodwrite_logs
(self, loss, logits, targets)
ldm/models/diffusion/classifier.py:162
↓ 1 callersFunctionwrite_pfm
Write pfm file. Args: path (str): pathto file image (array): data scale (int, optional): Scale. Defaults to 1.
annotator/zoe/zoedepth/models/base_models/midas_repo/tf/utils.py:6
FunctionDPT_BEiT_B_384
# This docstring shows up in hub.help() MiDaS DPT_BEiT_B_384 model for monocular depth estimation pretrained (bool): load pretrained weights
annotator/zoe/zoedepth/models/base_models/midas_repo/hubconf.py:55
FunctionDPT_BEiT_L_384
# This docstring shows up in hub.help() MiDaS DPT_BEiT_L_384 model for monocular depth estimation pretrained (bool): load pretrained weights
annotator/zoe/zoedepth/models/base_models/midas_repo/hubconf.py:32
FunctionDPT_BEiT_L_512
# This docstring shows up in hub.help() MiDaS DPT_BEiT_L_512 model for monocular depth estimation pretrained (bool): load pretrained weights
annotator/zoe/zoedepth/models/base_models/midas_repo/hubconf.py:9
FunctionDPT_Hybrid
# This docstring shows up in hub.help() MiDaS DPT-Hybrid model for monocular depth estimation pretrained (bool): load pretrained weights into
annotator/zoe/zoedepth/models/base_models/midas_repo/hubconf.py:241
FunctionDPT_Large
# This docstring shows up in hub.help() MiDaS DPT-Large model for monocular depth estimation pretrained (bool): load pretrained weights into
annotator/zoe/zoedepth/models/base_models/midas_repo/hubconf.py:218
FunctionDPT_LeViT_224
# This docstring shows up in hub.help() MiDaS DPT_LeViT_224 model for monocular depth estimation pretrained (bool): load pretrained weights i
annotator/zoe/zoedepth/models/base_models/midas_repo/hubconf.py:193
← previousnext →301–400 of 1,051, ranked by callers