MCPcopy Create free account

hub / github.com/baaivision/GeoDream / functions

Functions3,158 in github.com/baaivision/GeoDream

⨍ Functions 3,158◇ Types & classes 664↳ Endpoints 1
↓ 3 callersFunctioncheckpoint
Evaluate a function without caching intermediate activations, allowing for reduced memory at the expense of extra compute in the backward pas
mv-diffusion/One-2-3-45-by-view/ldm/modules/diffusionmodules/util.py:102
↓ 3 callersMethodcopy_to
(self, model)
extern/ldm_zero123/modules/ema.py:52
↓ 3 callersFunctioncount_params
(model, verbose=False)
extern/ldm_zero123/util.py:91
↓ 3 callersFunctioncount_params
(model, verbose=False)
mv-diffusion/One-2-3-45-by-view/ldm/util.py:124
↓ 3 callersFunctioncreate_window
(window_size, channel)
extern/ldm_zero123/modules/evaluate/ssim.py:23
↓ 3 callersFunctioncreate_window
(window_size, channel)
mv-diffusion/One-2-3-45-by-view/ldm/modules/evaluate/ssim.py:22
↓ 3 callersFunctioncrop_around_box
(tensor, bbox, impath="")
threestudio/data/co3d.py:100
↓ 3 callersFunctiondefault
(val, d)
extern/ldm_zero123/modules/attention.py:20
↓ 3 callersFunctiondefault
(val, d)
mv-diffusion/One-2-3-45-by-view/ldm/modules/attention.py:19
↓ 3 callersFunctiondefault
(val, d)
threestudio/utils/GAN/attention.py:20
↓ 3 callersMethodencode
(self, x)
mv-diffusion/One-2-3-45-by-view/ldm/models/autoencoder.py:96
↓ 3 callersFunctionexists
(val)
extern/ldm_zero123/modules/attention.py:12
↓ 3 callersFunctionexists
(val)
mv-diffusion/One-2-3-45-by-view/ldm/modules/attention.py:11
↓ 3 callersMethodforward_density
(self, points: Float[Tensor, "*N Di"])
threestudio/models/geometry/implicit_volume.py:195
↓ 3 callersMethodforward_unet
( self, unet: UNet2DConditionModel, latents: Float[Tensor, "..."], t: Float[Te
threestudio/models/guidance/stable_diffusion_vsd_guidance.py:400
↓ 3 callersMethodforward_unet
( self, unet: UNet2DConditionModel, latents: Float[Tensor, "..."], t: Int[Tens
threestudio/models/guidance/zero123_unified_guidance.py:288
↓ 3 callersMethodforward_unet
( self, unet: UNet2DConditionModel, latents: Float[Tensor, "..."], t: Float[Te
threestudio/models/guidance/sd_vsd_scale_guidance.py:408
↓ 3 callersFunctionfspecial
python code from: https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filte
extern/ldm_zero123/modules/image_degradation/bsrgan_light.py:218
↓ 3 callersFunctionfspecial
python code from: https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filte
extern/ldm_zero123/modules/image_degradation/bsrgan.py:218
↓ 3 callersFunctionfspecial
python code from: https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filte
mv-diffusion/One-2-3-45-by-view/ldm/modules/image_degradation/bsrgan_light.py:210
↓ 3 callersFunctionfspecial
python code from: https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filte
mv-diffusion/One-2-3-45-by-view/ldm/modules/image_degradation/bsrgan.py:210
↓ 3 callersFunctiongen_random_rays_from_single_image
generate random rays in world space, for a single image :param H: :param W: :param N_rays: :param image: [3, H, W] :param int
mv-diffusion/One-2-3-45-by-view/reconstruction/models/rays.py:57
↓ 3 callersFunctiongen_random_rays_from_single_image
generate random rays in world space, for a single image :param H: :param W: :param N_rays: :param image: [3, H, W] :param int
mv-diffusion/One-2-3-45/reconstruction/models/rays.py:57
↓ 3 callersMethodget_conditional_volume
:param feature_maps: pyramid features (B,V,C0+C1+C2,H,W) fused pyramid features :param partial_vol_origin: [B, 3] the world coordin
mv-diffusion/One-2-3-45-by-view/reconstruction/models/sparse_sdf_network.py:285
↓ 3 callersMethodget_fold_unfold
:param x: img of size (bs, c, h, w) :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])
extern/ldm_zero123/models/diffusion/ddpm.py:836
↓ 3 callersMethodget_fold_unfold
:param x: img of size (bs, c, h, w) :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])
mv-diffusion/One-2-3-45-by-view/ldm/models/diffusion/ddpm.py:669
↓ 3 callersMethodget_input
(self, batch, k)
extern/ldm_zero123/models/autoencoder.py:134
↓ 3 callersMethodget_input
(self, batch, k)
extern/ldm_zero123/models/autoencoder.py:402
↓ 3 callersMethodget_input
(self, batch, k)
mv-diffusion/MVDream/mvdream/ldm/models/autoencoder.py:101
↓ 3 callersMethodget_input
(self, batch, k)
mv-diffusion/One-2-3-45-by-view/ldm/models/autoencoder.py:124
↓ 3 callersMethodget_input
(self, batch, k)
mv-diffusion/One-2-3-45-by-view/ldm/models/autoencoder.py:344
↓ 3 callersMethodget_loss
(self, pred, target, mean=True)
extern/ldm_zero123/models/diffusion/ddpm.py:433
↓ 3 callersMethodget_loss
(self, pred, target, mean=True)
mv-diffusion/One-2-3-45-by-view/ldm/models/diffusion/ddpm.py:329
↓ 3 callersFunctionget_projection_matrix
( fovy: Float[Tensor, "B"], aspect_wh: float, near: float, far: float )
threestudio/utils/ops.py:266
↓ 3 callersMethodget_rgb_image_
(self, img, data_format, data_range, rgba=False)
threestudio/utils/saving.py:77
↓ 3 callersMethodget_shifted_sdf
( self, points: Float[Tensor, "*N Di"], sdf: Float[Tensor, "*N 1"] )
threestudio/models/geometry/implicit_sdf.py:224
↓ 3 callersFunctionget_shifts
(x)
mv-diffusion/One-2-3-45-by-view/reconstruction/ops/grid_sampler.py:359
↓ 3 callersFunctionget_shifts
(x)
mv-diffusion/One-2-3-45/reconstruction/ops/grid_sampler.py:359
↓ 3 callersFunctionget_shifts
(x)
threestudio/models/geometry/grid_sampler.py:359
↓ 3 callersFunctionget_weight
(s, a=-0.5)
mv-diffusion/One-2-3-45-by-view/reconstruction/ops/grid_sampler.py:220
↓ 3 callersMethodget_weighting
(self, h, w, Ly, Lx, device)
extern/ldm_zero123/models/diffusion/ddpm.py:815
↓ 3 callersMethodget_weighting
(self, h, w, Ly, Lx, device)
mv-diffusion/One-2-3-45-by-view/ldm/models/diffusion/ddpm.py:653
↓ 3 callersFunctioninstantiate_from_config
(config)
mv-diffusion/MVDream/mvdream/ldm/modules/diffusionmodules/util.py:19
↓ 3 callersFunctioninstantiate_from_config
(config)
threestudio/utils/GAN/util.py:78
↓ 3 callersFunctionload_module_weights
( path, module_name=None, ignore_modules=None, map_location=None )
threestudio/utils/misc.py:32
↓ 3 callersMethodmake_linear
(self, dim_in, dim_out, is_first, is_last)
threestudio/models/networks.py:182
↓ 3 callersMethodmake_linear
(self, dim_in, dim_out, is_first, is_last)
threestudio/models/networks.py:226
↓ 3 callersMethodmake_loader
(self, dataset_config, train=True)
mv-diffusion/One-2-3-45-by-view/ldm/data/laion.py:125
↓ 3 callersFunctionmake_tranforms
(image_transforms)
mv-diffusion/One-2-3-45-by-view/ldm/data/simple.py:103
↓ 3 callersMethodmodify_score
(self, model, e_t, x, t, c)
extern/ldm_zero123/guidance.py:59
↓ 3 callersFunctionnormalize
(vectors)
mv-diffusion/One-2-3-45-by-view/utils/utils.py:82
↓ 3 callersFunctionnormalize
(vectors)
mv-diffusion/One-2-3-45/utils/utils.py:82
↓ 3 callersMethodobtain_pyramid_feature_maps
get feature maps of all conditional images :param imgs: :return:
mv-diffusion/One-2-3-45-by-view/reconstruction/models/trainer_generic.py:593
↓ 3 callersFunctionparse_scheduler
(config, optimizer)
threestudio/systems/utils.py:74
↓ 3 callersFunctionperceptual_sim
(img1, img2, vgg16)
extern/ldm_zero123/modules/evaluate/evaluate_perceptualsim.py:315
↓ 3 callersFunctionperceptual_sim
(img1, img2, vgg16)
mv-diffusion/One-2-3-45-by-view/ldm/modules/evaluate/evaluate_perceptualsim.py:328
↓ 3 callersMethodpredict_start_from_noise
(self, x_t, t, noise)
mv-diffusion/One-2-3-45-by-view/ldm/models/diffusion/ddpm.py:266
↓ 3 callersMethodprepare_latents
( self, batch_size, num_channels_latents, height, width, dtype
extern/zero123.py:371
↓ 3 callersFunctionpsnr
(img1, img2, mask=None, reshape=False)
extern/ldm_zero123/modules/evaluate/evaluate_perceptualsim.py:291
↓ 3 callersFunctionpsnr
(img1, img2, mask=None,reshape=False)
mv-diffusion/One-2-3-45-by-view/ldm/modules/evaluate/evaluate_perceptualsim.py:304
↓ 3 callersFunctionrenew_attention_paths
Updates paths inside attentions to the new naming scheme (local renaming)
scripts/convert_zero123_to_diffusers.py:240
↓ 3 callersFunctionresize_image
(image, height, width, mode="bilinear")
threestudio/data/co3d.py:107
↓ 3 callersFunctionsample_model_batch
(args, model, sampler, input_im, xs, ys, n_samples=4, precision='autocast', ddim_eta=1.0, ddim_steps=75, scale
mv-diffusion/One-2-3-45-by-view/utils/zero123_utils.py:60
↓ 3 callersFunctionsample_model_batch
(model, sampler, input_im, xs, ys, n_samples=4, precision='autocast', ddim_eta=1.0, ddim_steps=75, scale=3.0,
mv-diffusion/One-2-3-45/utils/zero123_utils.py:60
↓ 3 callersMethodset_min_max_steps
(self, min_step_percent=0.02, max_step_percent=0.98)
threestudio/models/guidance/zero123_guidance.py:145
↓ 3 callersFunctionset_system_status
(system: BaseSystem, ckpt_path: Optional[str])
launch.py:173
↓ 3 callersMethodshared_step
(self, batch)
extern/ldm_zero123/models/diffusion/ddpm.py:495
↓ 3 callersMethodshared_step
(self, batch)
mv-diffusion/One-2-3-45-by-view/ldm/models/diffusion/ddpm.py:387
↓ 3 callersFunctionsparse_to_dense_volume
convert the sparse volume into dense volume to enable trilinear sampling to save GPU memory; :param coords: [num_pts, 3] :param featu
mv-diffusion/One-2-3-45-by-view/reconstruction/models/sparse_sdf_network.py:508
↓ 3 callersFunctionsparse_to_dense_volume
convert the sparse volume into dense volume to enable trilinear sampling to save GPU memory; :param coords: [num_pts, 3] :param featu
mv-diffusion/One-2-3-45/reconstruction/models/sparse_sdf_network.py:502
↓ 3 callersFunctionssim
(img1, img2)
extern/ldm_zero123/modules/image_degradation/utils_image.py:728
↓ 3 callersFunctionssim
(img1, img2)
mv-diffusion/One-2-3-45-by-view/ldm/modules/image_degradation/utils_image.py:669
↓ 3 callersFunctionssim_metric
(img1, img2, mask=None)
extern/ldm_zero123/modules/evaluate/evaluate_perceptualsim.py:286
↓ 3 callersFunctionssim_metric
(img1, img2, mask=None)
mv-diffusion/One-2-3-45-by-view/ldm/modules/evaluate/evaluate_perceptualsim.py:299
↓ 3 callersFunctiontimestep_embedding
Create sinusoidal timestep embeddings. :param timesteps: a 1-D Tensor of N indices, one per batch element. These may be
mv-diffusion/MVDream/mvdream/ldm/modules/diffusionmodules/util.py:165
↓ 3 callersMethodto_rgb
(self, x)
extern/ldm_zero123/models/autoencoder.py:312
↓ 3 callersMethodto_rgb
(self, x)
mv-diffusion/MVDream/mvdream/ldm/models/autoencoder.py:191
↓ 3 callersMethodto_rgb
(self, x)
mv-diffusion/One-2-3-45-by-view/ldm/models/autoencoder.py:255
↓ 3 callersMethodupsample
:param pre_feat: (Tensor), features from last level, (N, C) :param pre_coords: (Tensor), coordinates from last level, (N, 4) (4 : Ba
mv-diffusion/One-2-3-45-by-view/reconstruction/models/sparse_sdf_network.py:197
↓ 3 callersMethodvalidate
(self, resolution_level=-1)
mv-diffusion/One-2-3-45/reconstruction/exp_runner_generic_blender_val.py:514
↓ 3 callersFunctionvalidate_empty_rays
(ray_indices, t_start, t_end)
threestudio/utils/ops.py:444
↓ 3 callersFunctionzero123_infer
(args, model, input_dir_path, start_idx=0, end_idx=12, indices=None, device="cuda", ddim_steps=75, scale=3.0)
mv-diffusion/One-2-3-45-by-view/utils/zero123_utils.py:171
↓ 2 callersFunctionNormalize
(in_channels)
extern/ldm_zero123/modules/attention.py:76
↓ 2 callersFunctionNormalize
(in_channels)
mv-diffusion/One-2-3-45-by-view/ldm/modules/attention.py:76
↓ 2 callersFunctionNormalize
(in_channels)
threestudio/utils/GAN/attention.py:76
↓ 2 callersMethod__init__
(self, channels, reduction)
extern/ldm_zero123/thirdp/psp/helpers.py:76
↓ 2 callersMethod__init__
(self, in_channels, out_channels, kernel_size=3, stride=1, pad=1, norm_act=I
mv-diffusion/One-2-3-45-by-view/reconstruction/models/featurenet.py:13
↓ 2 callersMethod__init__
Returns only captions with dummy images
mv-diffusion/One-2-3-45-by-view/ldm/data/simple.py:474
↓ 2 callersMethod__init__
(self, channels, reduction)
mv-diffusion/One-2-3-45-by-view/ldm/thirdp/psp/helpers.py:59
↓ 2 callersMethod__init__
(self, in_channels, out_channels, kernel_size=3, stride=1, pad=1, norm_act=I
mv-diffusion/One-2-3-45/reconstruction/models/featurenet.py:13
↓ 2 callersMethod__init__
( self, cfg: Optional[Union[dict, DictConfig]] = None, *args, **kwargs )
threestudio/utils/base.py:77
↓ 2 callersMethod__init__
(self, save_path)
threestudio/utils/callbacks.py:122
↓ 2 callersMethod__init__
(self, cfg: Any, split: str)
threestudio/data/image.py:273
↓ 2 callersMethod__init__
(self, cfg: Any, split: str)
threestudio/data/multiview.py:197
↓ 2 callersMethod__init__
(self, cfg: Any, split: str)
threestudio/data/uncond.py:407
↓ 2 callersMethod__init__
(self)
threestudio/models/geometry/geodream_geometry_volume.py:343
↓ 2 callersFunction_batch_pairwise_distances
Compute pairwise distances between two batches of feature vectors.
extern/ldm_zero123/modules/evaluate/adm_evaluator.py:463
↓ 2 callersFunction_batch_pairwise_distances
Compute pairwise distances between two batches of feature vectors.
mv-diffusion/One-2-3-45-by-view/ldm/modules/evaluate/adm_evaluator.py:436
↓ 2 callersFunction_distributed_available
()
threestudio/utils/misc.py:104
↓ 2 callersFunction_download_inception_model
()
extern/ldm_zero123/modules/evaluate/adm_evaluator.py:622
← previousnext →301–400 of 3,158, ranked by callers