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
↓ 5 callersFunctionlinear
Create a linear module.
mv-diffusion/One-2-3-45-by-view/ldm/modules/diffusionmodules/util.py:231
↓ 5 callersFunctionload_config
(*yamls: str, cli_args: list = [], from_string=False, **kwargs)
threestudio/utils/config.py:99
↓ 5 callersFunctionmake_divisible
(x, divisible_by=8)
threestudio/utils/GAN/mobilenet.py:78
↓ 5 callersMethodmaterial
(self)
threestudio/models/renderers/base.py:58
↓ 5 callersMethodmode
(self)
extern/ldm_zero123/modules/distributions/distributions.py:20
↓ 5 callersMethodquantize
(self, x, *args, **kwargs)
extern/ldm_zero123/models/autoencoder.py:545
↓ 5 callersMethodquantize
(self, x, *args, **kwargs)
mv-diffusion/One-2-3-45-by-view/ldm/models/autoencoder.py:437
↓ 5 callersMethodsample
(self, S, batch_size, shape, conditioning=None,
mv-diffusion/MVDream/mvdream/ldm/models/diffusion/ddim.py:56
↓ 5 callersFunctionshave_segments
Removes segments. Positive values shave the first segments, negative shave the last segments.
scripts/convert_zero123_to_diffusers.py:206
↓ 5 callersFunctionsparse_to_dense_channel
(locs, values, dim, c, default_val, device)
mv-diffusion/One-2-3-45-by-view/reconstruction/tsparse/torchsparse_utils.py:125
↓ 5 callersFunctionsparse_to_dense_channel
(locs, values, dim, c, default_val, device)
mv-diffusion/One-2-3-45/reconstruction/tsparse/torchsparse_utils.py:125
↓ 4 callersMethod__init__
(self, pnet_type="vgg", pnet_rand=False, use_gpu=True)
extern/ldm_zero123/modules/evaluate/evaluate_perceptualsim.py:230
↓ 4 callersMethod__init__
(self, volume, coords=None, type='dense')
mv-diffusion/One-2-3-45-by-view/reconstruction/models/sparse_sdf_network.py:544
↓ 4 callersMethod__init__
(self, pnet_type="vgg", pnet_rand=False, use_gpu=True)
mv-diffusion/One-2-3-45-by-view/ldm/modules/evaluate/evaluate_perceptualsim.py:237
↓ 4 callersMethod__init__
Imagenet Superresolution Dataloader Performs following ops in order: 1. crops a crop of size s from image either as random o
mv-diffusion/One-2-3-45-by-view/ldm/data/imagenet.py:273
↓ 4 callersMethod__init__
(self, size=None, dataroot="", datajson="", onehot_segmentation=False, use_stuffthing=False,
mv-diffusion/One-2-3-45-by-view/ldm/data/coco.py:13
↓ 4 callersMethod__init__
(self, volume, coords=None, type='dense')
mv-diffusion/One-2-3-45/reconstruction/models/sparse_sdf_network.py:538
↓ 4 callersMethod__init__
( self, num_features, logdet=False, affine=True, allow_reverse_init=False )
threestudio/utils/GAN/discriminator.py:13
↓ 4 callersMethod_save_rgb_image
( self, filename, img, data_format, data_range, name: Optional
threestudio/utils/saving.py:111
↓ 4 callersFunctionadd_Gaussian_noise
(img, noise_level1=2, noise_level2=25)
extern/ldm_zero123/modules/image_degradation/bsrgan.py:389
↓ 4 callersFunctionadd_Gaussian_noise
(img, noise_level1=2, noise_level2=25)
mv-diffusion/One-2-3-45-by-view/ldm/modules/image_degradation/bsrgan.py:369
↓ 4 callersFunctionadd_JPEG_noise
(img)
extern/ldm_zero123/modules/image_degradation/bsrgan_light.py:453
↓ 4 callersFunctionadd_JPEG_noise
(img)
mv-diffusion/One-2-3-45-by-view/ldm/modules/image_degradation/bsrgan_light.py:422
↓ 4 callersFunctionadopt_weight
(weight, global_step, threshold=0, value=0.0)
extern/ldm_zero123/modules/losses/vqperceptual.py:20
↓ 4 callersFunctionadopt_weight
(weight, global_step, threshold=0, value=0.)
mv-diffusion/One-2-3-45-by-view/ldm/modules/losses/vqperceptual.py:20
↓ 4 callersMethodbackward
(ctx, *output_grads)
mv-diffusion/One-2-3-45-by-view/ldm/modules/diffusionmodules/util.py:131
↓ 4 callersFunctionbicubic_interpolate
two dimensional cubic interpolation :param p: [N, 4, 4] :param x: [N] :param y: [N] :return:
mv-diffusion/One-2-3-45-by-view/reconstruction/ops/grid_sampler.py:253
↓ 4 callersFunctionbicubic_interpolate
two dimensional cubic interpolation :param p: [N, 4, 4] :param x: [N] :param y: [N] :return:
mv-diffusion/One-2-3-45/reconstruction/ops/grid_sampler.py:253
↓ 4 callersFunctionbicubic_interpolate
two dimensional cubic interpolation :param p: [N, 4, 4] :param x: [N] :param y: [N] :return:
threestudio/models/geometry/grid_sampler.py:253
↓ 4 callersFunctioncalculate_weights_indices
( in_length, out_length, scale, kernel, kernel_width, antialiasing )
extern/ldm_zero123/modules/image_degradation/utils_image.py:769
↓ 4 callersFunctioncalculate_weights_indices
(in_length, out_length, scale, kernel, kernel_width, antialiasing)
mv-diffusion/One-2-3-45-by-view/ldm/modules/image_degradation/utils_image.py:708
↓ 4 callersFunctioncartesian_to_spherical
(xyz)
mv-diffusion/One-2-3-45-by-view/ldm/data/nerf_like.py:11
↓ 4 callersMethodcompute_top_k
(self, logits, labels, k, reduction="mean")
extern/ldm_zero123/models/diffusion/classifier.py:181
↓ 4 callersMethodcompute_top_k
(self, logits, labels, k, reduction="mean")
mv-diffusion/One-2-3-45-by-view/ldm/models/diffusion/classifier.py:150
↓ 4 callersMethoddecode
(self, z)
mv-diffusion/MVDream/mvdream/ldm/models/autoencoder.py:87
↓ 4 callersMethoddecode_latents
( self, latents: Float[Tensor, "B 4 H W"], latent_height: int = 64, latent_wid
threestudio/models/guidance/stable_diffusion_guidance.py:170
↓ 4 callersMethodema_scope
(self, context=None)
mv-diffusion/One-2-3-45-by-view/ldm/models/autoencoder.py:64
↓ 4 callersMethodencode
( self, x0, c, t_enc, use_original_steps=False, return_interme
extern/ldm_zero123/models/diffusion/ddim.py:362
↓ 4 callersMethodencode
(self, x0, c, t_enc, use_original_steps=False, return_intermediates=None, unconditional_guidanc
mv-diffusion/One-2-3-45-by-view/ldm/models/diffusion/ddim.py:246
↓ 4 callersMethodforward
(self, img1, img2, mask=None)
extern/ldm_zero123/modules/evaluate/ssim.py:84
↓ 4 callersMethodforward
(self, img1, img2, mask=None)
mv-diffusion/One-2-3-45-by-view/ldm/modules/evaluate/ssim.py:87
↓ 4 callersMethodforward_unet
( self, unet: UNet2DConditionModel, latents: Float[Tensor, "..."], t: Int[Tens
threestudio/models/guidance/stable_diffusion_unified_guidance.py:277
↓ 4 callersMethodforward_unet
( self, latents: Float[Tensor, "..."], t: Float[Tensor, "..."], encoder_hidden
threestudio/models/guidance/deep_floyd_guidance.py:113
↓ 4 callersMethodgeneral_loader
(self, dataset, batch_size, collate_fn=None)
threestudio/data/image.py:319
↓ 4 callersMethodgeneral_loader
(self, dataset, batch_size, collate_fn=None)
threestudio/data/multiview.py:400
↓ 4 callersMethodgeneral_loader
(self, dataset, batch_size, collate_fn=None)
threestudio/data/uncond.py:542
↓ 4 callersMethodgeneral_loader
(self, dataset, batch_size, collate_fn=None)
threestudio/data/co3d.py:691
↓ 4 callersMethodget_last_layer
(self)
extern/ldm_zero123/models/autoencoder.py:286
↓ 4 callersMethodget_last_layer
(self)
extern/ldm_zero123/models/autoencoder.py:505
↓ 4 callersMethodget_last_layer
(self)
mv-diffusion/MVDream/mvdream/ldm/models/autoencoder.py:162
↓ 4 callersMethodget_last_layer
(self)
mv-diffusion/One-2-3-45-by-view/ldm/models/autoencoder.py:230
↓ 4 callersMethodget_last_layer
(self)
mv-diffusion/One-2-3-45-by-view/ldm/models/autoencoder.py:397
↓ 4 callersFunctionget_stats
(stats)
extern/ldm_zero123/modules/evaluate/torch_frechet_video_distance.py:168
↓ 4 callersFunctionget_stats
(stats)
mv-diffusion/One-2-3-45-by-view/ldm/modules/evaluate/torch_frechet_video_distance.py:142
↓ 4 callersMethodget_text_embeddings_perp_neg
( self, elevation: Float[Tensor, "B"], azimuth: Float[Tensor, "B"], camera_dis
threestudio/models/prompt_processors/base.py:80
↓ 4 callersMethodget_trilinear_feature
( self, points: Float[Tensor, "*N Di"], grid: Float[Tensor, "1 Df G1 G2 G3"] )
threestudio/models/geometry/volume_grid.py:65
↓ 4 callersFunctiongrid_sample_3d
bilinear sampling cannot guarantee continuous first-order gradient mimic pytorch grid_sample function The 8 corner points of a volume not
mv-diffusion/One-2-3-45-by-view/reconstruction/ops/grid_sampler.py:64
↓ 4 callersFunctiongrid_sample_3d
bilinear sampling cannot guarantee continuous first-order gradient mimic pytorch grid_sample function The 8 corner points of a volume not
mv-diffusion/One-2-3-45/reconstruction/ops/grid_sampler.py:64
↓ 4 callersFunctionhash_prompt
(model: str, prompt: str)
threestudio/models/prompt_processors/base.py:19
↓ 4 callersMethodinterpolate_one
( self, attr: Float[Tensor, "Nv C"], rast: Float[Tensor, "B H W 4"], tri: Inte
threestudio/utils/rasterize.py:70
↓ 4 callersMethodload_from_cache
(self, prompt)
threestudio/models/prompt_processors/base.py:433
↓ 4 callersMethodload_im
replace background pixel with random color in rendering
mv-diffusion/One-2-3-45-by-view/ldm/data/simple.py:274
↓ 4 callersMethodmodify_score
(self, model, e_t, x, t, c)
mv-diffusion/One-2-3-45-by-view/ldm/guidance.py:57
↓ 4 callersFunctionnoise_like
(shape, device, repeat=False)
extern/ldm_zero123/modules/diffusionmodules/util.py:291
↓ 4 callersFunctionnoise_like
(shape, device, repeat=False)
mv-diffusion/One-2-3-45-by-view/ldm/modules/diffusionmodules/util.py:264
↓ 4 callersMethodpreprocess_data
(self, batch, stage)
threestudio/systems/base.py:166
↓ 4 callersMethodprocess_im
(self, im)
mv-diffusion/One-2-3-45-by-view/ldm/data/simple.py:328
↓ 4 callersFunctionrenew_vae_resnet_paths
Updates paths inside resnets to the new naming scheme (local renaming)
scripts/convert_zero123_to_diffusers.py:809
↓ 4 callersFunctionretrieve
Given a nested list or dict return the desired value at key expanding callable nodes if necessary and :attr:`expand` is ``True``. The expansion
threestudio/utils/perceptual/utils.py:58
↓ 4 callersMethodsample
(self, batch_size=16, return_intermediates=False)
extern/ldm_zero123/models/diffusion/ddpm.py:417
↓ 4 callersFunctionsample_ptsFeatures_from_featureVolume
sample feature of pts_wrd from featureVolume, all in world space :param pts: [N_rays, n_samples, 3] :param featureVolume: [C,wX,wY,wZ]
mv-diffusion/One-2-3-45-by-view/reconstruction/models/render_utils.py:54
↓ 4 callersFunctionsample_ptsFeatures_from_featureVolume
sample feature of pts_wrd from featureVolume, all in world space :param pts: [N_rays, n_samples, 3] :param featureVolume: [C,wX,wY,wZ]
mv-diffusion/One-2-3-45/reconstruction/models/render_utils.py:54
↓ 4 callersMethodshared_step
(self, batch, t=None)
extern/ldm_zero123/models/diffusion/classifier.py:214
↓ 4 callersMethodshared_step
(self, batch, t=None)
mv-diffusion/One-2-3-45-by-view/ldm/models/diffusion/classifier.py:179
↓ 4 callersFunctionshifted_expotional_decay
(a, b, c, r)
threestudio/utils/ops.py:423
↓ 4 callersMethodstep
Performs a single optimization step. Args: closure (callable, optional): A closure that reevaluates the model and
mv-diffusion/One-2-3-45-by-view/ldm/util.py:178
↓ 4 callersFunctionupdate_end_if_possible
(module: Any, epoch: int, global_step: int)
threestudio/utils/base.py:65
↓ 4 callersFunctionupdate_if_possible
(module: Any, epoch: int, global_step: int)
threestudio/utils/base.py:60
↓ 4 callersFunctionvolsdf_density
(sdf, inv_std)
threestudio/models/renderers/neus_volume_renderer.py:19
↓ 4 callersFunctionvoxel_to_point
(x, z, nearest=False)
mv-diffusion/One-2-3-45-by-view/reconstruction/tsparse/torchsparse_utils.py:70
↓ 4 callersFunctionvoxel_to_point
(x, z, nearest=False)
mv-diffusion/One-2-3-45/reconstruction/tsparse/torchsparse_utils.py:70
↓ 4 callersFunctionzero_module
Zero out the parameters of a module and return it.
extern/ldm_zero123/modules/diffusionmodules/util.py:201
↓ 4 callersFunctionzero_module
Zero out the parameters of a module and return it.
mv-diffusion/MVDream/mvdream/ldm/modules/attention.py:79
↓ 4 callersFunctionzero_module
Zero out the parameters of a module and return it.
mv-diffusion/MVDream/mvdream/ldm/modules/diffusionmodules/util.py:189
↓ 4 callersFunctionzero_module
Zero out the parameters of a module and return it.
mv-diffusion/One-2-3-45-by-view/ldm/modules/diffusionmodules/util.py:174
↓ 3 callersFunctionC_max
(value: Any)
threestudio/utils/config.py:31
↓ 3 callersFunctionNormalize
(in_channels)
mv-diffusion/MVDream/mvdream/ldm/modules/attention.py:88
↓ 3 callersMethod__init__
( self, ddconfig, lossconfig, n_embed, embed_dim, ckpt_path=No
extern/ldm_zero123/models/autoencoder.py:16
↓ 3 callersMethod__init__
(self)
mv-diffusion/One-2-3-45-by-view/reconstruction/loss/color_loss.py:7
↓ 3 callersMethod__init__
(self, factor, output_size, initial_size=None, image_key="jpg")
mv-diffusion/One-2-3-45-by-view/ldm/data/laion.py:225
↓ 3 callersMethod__init__
(self, ddconfig, lossconfig, n_embed, embe
mv-diffusion/One-2-3-45-by-view/ldm/models/autoencoder.py:15
↓ 3 callersMethod__init__
(self)
mv-diffusion/One-2-3-45/reconstruction/loss/color_loss.py:7
↓ 3 callersMethod__init__
(self, requires_grad=False, pretrained=True)
threestudio/utils/perceptual/perceptual.py:100
↓ 3 callersMethod_isosurface
(self, bbox: Float[Tensor, "2 3"], fine_stage: bool = False)
threestudio/models/geometry/base.py:119
↓ 3 callersMethod_save_grayscale_image
( self, filename, img, data_range, cmap, name: Optional[str] =
threestudio/utils/saving.py:223
↓ 3 callersMethod_unwrap_uv
( self, xatlas_chart_options: dict = {}, xatlas_pack_options: dict = {} )
threestudio/models/mesh.py:207
↓ 3 callersFunctionadd_blur
(img, sf=4)
extern/ldm_zero123/modules/image_degradation/bsrgan_light.py:335
↓ 3 callersFunctionadd_blur
(img, sf=4)
mv-diffusion/One-2-3-45-by-view/ldm/modules/image_degradation/bsrgan_light.py:325
↓ 3 callersMethodantialias
( self, color: Float[Tensor, "B H W C"], rast: Float[Tensor, "B H W 4"], pos:
threestudio/utils/rasterize.py:49
↓ 3 callersFunctioncheckpoint
Evaluate a function without caching intermediate activations, allowing for reduced memory at the expense of extra compute in the backward pas
extern/ldm_zero123/modules/diffusionmodules/util.py:125
← previousnext →201–300 of 3,158, ranked by callers