MCPcopy Create free account

hub / github.com/MegaScenes/nvs / functions

Functions1,032 in github.com/MegaScenes/nvs

⨍ Functions 1,032◇ Types & classes 170
↓ 1 callersFunctionequals
(val)
ldm/modules/x_transformer.py:76
↓ 1 callersFunctionexample03
()
ldm/data/laion.py:457
↓ 1 callersFunctionfilter_size
(x)
ldm/data/laion.py:468
↓ 1 callersFunctionfilter_watermark
(x)
ldm/data/laion.py:474
↓ 1 callersMethodforward
(self, x)
ldm/modules/diffusionmodules/util.py:210
↓ 1 callersFunctionfov_from_intrinsics
(intrinsics)
dataloader/data_helpers.py:708
↓ 1 callersMethodfreeze
(self)
ldm/modules/encoders/modules.py:198
↓ 1 callersMethodfreeze
(self)
ldm/modules/encoders/modules.py:285
↓ 1 callersFunctionfspecial_gaussian
(hsize, sigma)
ldm/modules/image_degradation/bsrgan_light.py:187
↓ 1 callersFunctionfspecial_gaussian
(hsize, sigma)
ldm/modules/image_degradation/bsrgan.py:187
↓ 1 callersFunctionfspecial_laplacian
(alpha)
ldm/modules/image_degradation/bsrgan_light.py:201
↓ 1 callersFunctionfspecial_laplacian
(alpha)
ldm/modules/image_degradation/bsrgan.py:201
↓ 1 callersFunctiongaussian
(window_size, sigma)
ldm/modules/evaluate/ssim.py:12
↓ 1 callersFunctiongen_box_mask
(mask, masked)
ldm/data/inpainting/synthetic_mask.py:66
↓ 1 callersMethodgen_fn
()
ldm/modules/evaluate/adm_evaluator.py:465
↓ 1 callersFunctiongen_round_mask
(mask, masked, radius)
ldm/data/inpainting/synthetic_mask.py:72
↓ 1 callersFunctiongen_segment_mask
(mask, start, end, brush_width)
ldm/data/inpainting/synthetic_mask.py:56
↓ 1 callersFunctiongenerate_faces
(H, W)
dataloader/util_3dphoto.py:41
↓ 1 callersMethodget_T
(self, target_RT, cond_RT)
ldm/data/backup_simple.py:257
↓ 1 callersFunctionget_T_torch
(target_inhomogeneous_world2cam, cond_inhomogeneous_world2cam)
ldm/data/common.py:84
↓ 1 callersFunctionget_aligned_monodepths
(depth_model, batch)
ldm/data/common.py:182
↓ 1 callersMethodget_base
(self)
ldm/data/imagenet.py:379
↓ 1 callersFunctionget_blocks
(num_layers)
ldm/thirdp/psp/helpers.py:31
↓ 1 callersFunctionget_ccw_poses
(num_steps=10, radius=1, rotation_angle=30, zscale=1, xscale=1, c2w=True, endpoint=(0,-1))
dataloader/evalhelpers.py:30
↓ 1 callersFunctionget_cw_poses
(num_steps=10, radius=1, rotation_angle=30, zscale=1, xscale=1, c2w=True, endpoint=(0,1))
dataloader/evalhelpers.py:59
↓ 1 callersFunctionget_front_facing_trans
(num_frames, max_trans=2.0, c2w=True, z_div=2.0)
dataloader/evalhelpers.py:96
↓ 1 callersFunctionget_image_paths
(dataroot)
ldm/modules/image_degradation/utils_image.py:67
↓ 1 callersMethodget_input
(self, batch, k, cond_key=None, bs=None, log_mode=False)
ldm/models/diffusion/backup_ddpm.py:1502
↓ 1 callersMethodget_input
(self, batch, k, cond_key=None, bs=None, return_first_stage_outputs=False)
ldm/models/diffusion/backup_ddpm.py:1683
↓ 1 callersMethodget_input
(self, batch, k, cond_key=None, bs=None, log_mode=False)
ldm/models/diffusion/backup_ddpm.py:1824
↓ 1 callersMethodget_input
(self, batch, k, cond_key=None, bs=None, log_mode=False)
ldm/models/diffusion/backup_ddpm.py:1916
↓ 1 callersMethodget_null_cond
(self, version, max_length)
ldm/modules/encoders/modules.py:322
↓ 1 callersFunctionget_obj_from_str
(string, reload=False)
ldm/util.py:160
↓ 1 callersFunctionget_orbit_poses
(cwx=(0,1), ccwx=(0,-1))
dataloader/evalhelpers.py:86
↓ 1 callersFunctionget_relative_transformations
(batch, scales)
dataloader/data_helpers.py:642
↓ 1 callersMethodget_scales
(self)
ldm/guidance.py:49
↓ 1 callersMethodget_split
(self)
ldm/data/coco.py:175
↓ 1 callersFunctionget_timestamp
()
ldm/modules/image_degradation/utils_image.py:33
↓ 1 callersFunctionget_timestep_embedding
This matches the implementation in Denoising Diffusion Probabilistic Models: From Fairseq. Build sinusoidal embeddings. This matches
ldm/modules/diffusionmodules/model.py:12
↓ 1 callersFunctionget_training_poses
()
dataloader/util_3dphoto.py:359
↓ 1 callersMethodget_unconditional_conditioning
(self, batch_size, null_label=None, image_size=512, concat_dim=4)
ldm/models/diffusion/ddpm.py:1460
↓ 1 callersMethodget_unconditional_conditioning
(self, batch_size, null_label=None, image_size=512)
ldm/models/diffusion/all_functions_ddpm.py:1336
↓ 1 callersMethodget_x_noisy
(self, x, t, noise=None)
ldm/models/diffusion/classifier.py:110
↓ 1 callersFunctiongm_blur_kernel
(mean, cov, size=15)
ldm/modules/image_degradation/bsrgan_light.py:86
↓ 1 callersFunctiongm_blur_kernel
(mean, cov, size=15)
ldm/modules/image_degradation/bsrgan.py:86
↓ 1 callersMethodimg_path_to_warped_path
get warped image given path1, path2; we used hashing to format the warped image
dataloader/paired_dataset.py:79
↓ 1 callersFunctionimread_uint
(path, n_channels=3)
ldm/modules/image_degradation/utils_image.py:185
↓ 1 callersFunctionimssave
imgs: list, N images of size WxHxC
ldm/modules/image_degradation/utils_image.py:112
↓ 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())
ldm/models/autoencoder.py:79
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list())
ldm/models/autoencoder.py:314
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list(), only_model=False)
ldm/models/diffusion/classifier.py:70
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list(), only_model=False)
ldm/models/diffusion/backup_ddpm.py:1653
↓ 1 callersMethodinstantiate_cond_stage
(self, config)
ldm/models/diffusion/ddpm.py:619
↓ 1 callersMethodinstantiate_cond_stage
(self, config)
ldm/models/diffusion/backup_ddpm.py:577
↓ 1 callersMethodinstantiate_cond_stage
(self, config)
ldm/models/diffusion/all_functions_ddpm.py:600
↓ 1 callersMethodinstantiate_extra_stage
(self, config)
ldm/models/diffusion/ddpm.py:643
↓ 1 callersMethodinstantiate_first_stage
(self, config)
ldm/models/diffusion/ddpm.py:596
↓ 1 callersMethodinstantiate_first_stage
(self, config)
ldm/models/diffusion/backup_ddpm.py:570
↓ 1 callersMethodinstantiate_first_stage
(self, config)
ldm/models/diffusion/all_functions_ddpm.py:577
↓ 1 callersMethodinstantiate_low_stage
(self, config)
ldm/models/diffusion/backup_ddpm.py:1494
↓ 1 callersMethodinstantiate_pretrained
(self, config)
ldm/modules/diffusionmodules/model.py:807
↓ 1 callersFunctioninvert_depth
(depth_map)
dataloader/evalhelpers.py:148
↓ 1 callersFunctionis_image_file
(filename)
ldm/modules/image_degradation/utils_image.py:29
↓ 1 callersMethodkl
(self, other=None)
ldm/modules/distributions/distributions.py:39
↓ 1 callersFunctionl2_norm
(input, axis=1)
ldm/thirdp/psp/helpers.py:17
↓ 1 callersMethodless_thans
(self, batch_1, radii_1, batch_2, radii_2)
ldm/modules/evaluate/adm_evaluator.py:424
↓ 1 callersMethodload_classifier
(self, ckpt_path, pool)
ldm/models/diffusion/classifier.py:95
↓ 1 callersFunctionload_depth_model
(depth_model_name)
ldm/data/common.py:124
↓ 1 callersMethodload_diffusion
(self)
ldm/models/diffusion/classifier.py:88
↓ 1 callersFunctionload_example
(example)
ldm/data/laion.py:382
↓ 1 callersFunctionload_img_and_intrinsics
1. load and resize img then center crop to target_res x target_res (e.g. 512x512) 2. scale focal length and principal point by how much img i
ldm/data/data_helpers.py:64
↓ 1 callersFunctionload_model_from_config
Loads a model from config and a ckpt if config is a path will use omegaconf to load
ldm/extras.py:55
↓ 1 callersMethodlog_images
(self, batch, only_inputs=False, plot_ema=False, **kwargs)
ldm/models/autoencoder.py:234
↓ 1 callersMethodlog_images
(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs)
ldm/models/diffusion/backup_ddpm.py:438
↓ 1 callersMethodlog_local
(self, split, images, epoch, foldername, returngrid, warpeddepth, has_target, returnimg, savegrid)
ldm/logger.py:32
↓ 1 callersFunctionmain
()
train.py:26
↓ 1 callersFunctionmain
()
test.py:31
↓ 1 callersFunctionmain
()
video_script.py:204
↓ 1 callersFunctionmain
()
ldm/modules/evaluate/adm_evaluator.py:31
↓ 1 callersMethodmake_cond_schedule
(self, )
ldm/models/diffusion/ddpm.py:565
↓ 1 callersMethodmake_cond_schedule
(self, )
ldm/models/diffusion/backup_ddpm.py:539
↓ 1 callersMethodmake_cond_schedule
(self, )
ldm/models/diffusion/all_functions_ddpm.py:546
↓ 1 callersFunctionmake_loader
(batch_size: int = 512)
evaluation/gen_metrics.py:102
↓ 1 callersFunctionmake_loader
()
evaluation/recon_metrics.py:105
↓ 1 callersFunctionmake_multi_folder_data
Make a concat dataset from multiple folders Don't suport captions yet If paths is a list, that's ok, if it's a Dict interpret it as: k=fo
ldm/data/backup_simple.py:113
↓ 1 callersMethodmake_schedule
(self, ddim_num_steps, ddim_discretize="uniform", ddim_eta=0., verbose=True)
ldm/models/diffusion/ddim.py:35
↓ 1 callersMethodmake_schedule
(self, ddim_num_steps, ddim_discretize="uniform", ddim_eta=0., verbose=True)
ldm/models/diffusion/plms.py:25
↓ 1 callersFunctionmake_tranforms
(image_transforms)
ldm/data/simple.py:33
↓ 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 callersMethodmeshgrid
(self, h, w)
ldm/models/diffusion/backup_ddpm.py:632
↓ 1 callersMethodmeshgrid
(self, h, w)
ldm/models/diffusion/all_functions_ddpm.py:658
↓ 1 callersFunctionnormalize_tensor
(tensor, to_zero_one, print_ratio=True, manual=None)
dataloader/data_helpers.py:165
↓ 1 callersFunctionnormalize_tensor
(tensor, to_zero_one, print_ratio=True, manual=None)
ldm/data/data_helpers.py:107
↓ 1 callersFunctionnot_equals
(val)
ldm/modules/x_transformer.py:70
↓ 1 callersMethodnp2pt
(self, x)
ldm/data/laion.py:235
↓ 1 callersFunctionopen_npz_array
(path: str, arr_name: str)
ldm/modules/evaluate/adm_evaluator.py:539
↓ 1 callersFunctionopen_url
Download the given URL and return a binary-mode file object to access the data.
ldm/modules/evaluate/torch_frechet_video_distance.py:41
← previousnext →301–400 of 1,032, ranked by callers