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
↓ 1 callersFunctionabs_error
(depth_pred, depth_gt, mask)
mv-diffusion/One-2-3-45-by-view/reconstruction/utils/misc_utils.py:72
↓ 1 callersFunctionabs_error
(depth_pred, depth_gt, mask)
mv-diffusion/One-2-3-45/reconstruction/utils/misc_utils.py:72
↓ 1 callersFunctionadd_hom
(pts)
mv-diffusion/One-2-3-45-by-view/reconstruction/models/patch_projector.py:164
↓ 1 callersFunctionadd_hom
(pts)
mv-diffusion/One-2-3-45/reconstruction/models/patch_projector.py:164
↓ 1 callersFunctionadd_margin
(pil_img, color, size=256)
mv-diffusion/One-2-3-45-by-view/ldm/util.py:38
↓ 1 callersFunctionadd_sharpening
USM sharpening. borrowed from real-ESRGAN Input image: I; Blurry image: B. 1. K = I + weight * (I - B) 2. Mask = 1 if abs(I - B) > thresho
extern/ldm_zero123/modules/image_degradation/bsrgan.py:309
↓ 1 callersFunctionadd_sharpening
USM sharpening. borrowed from real-ESRGAN Input image: I; Blurry image: B. 1. K = I + weight * (I - B) 2. Mask = 1 if abs(I - B) > thresho
mv-diffusion/One-2-3-45-by-view/ldm/modules/image_degradation/bsrgan.py:299
↓ 1 callersMethodadjust
(self)
mv-diffusion/One-2-3-45-by-view/reconstruction/loss/color_loss.py:133
↓ 1 callersMethodadjust
(self)
mv-diffusion/One-2-3-45/reconstruction/loss/color_loss.py:133
↓ 1 callersMethodaggregate_multiview_features
aggregate mutli-view features by compute their cost variance :param multiview_features: (num of voxels, num_of_views, c) :par
mv-diffusion/One-2-3-45-by-view/reconstruction/models/sparse_sdf_network.py:220
↓ 1 callersMethodaggregate_multiview_features
aggregate mutli-view features by compute their cost variance :param multiview_features: (num of voxels, num_of_views, c) :par
mv-diffusion/One-2-3-45/reconstruction/models/sparse_sdf_network.py:221
↓ 1 callersFunctionall_logging_disabled
A context manager that will prevent any logging messages triggered during the body from being processed. :param highest_level: the maxim
extern/ldm_zero123/extras.py:12
↓ 1 callersFunctionall_logging_disabled
A context manager that will prevent any logging messages triggered during the body from being processed. :param highest_level: the maxim
mv-diffusion/One-2-3-45-by-view/ldm/extras.py:12
↓ 1 callersFunctionanisotropic_Gaussian
generate an anisotropic Gaussian kernel Args: ksize : e.g., 15, kernel size theta : [0, pi], rotation angle range l1 :
extern/ldm_zero123/modules/image_degradation/bsrgan_light.py:65
↓ 1 callersFunctionanisotropic_Gaussian
generate an anisotropic Gaussian kernel Args: ksize : e.g., 15, kernel size theta : [0, pi], rotation angle range l1 :
extern/ldm_zero123/modules/image_degradation/bsrgan.py:65
↓ 1 callersFunctionanisotropic_Gaussian
generate an anisotropic Gaussian kernel Args: ksize : e.g., 15, kernel size theta : [0, pi], rotation angle range l1
mv-diffusion/One-2-3-45-by-view/ldm/modules/image_degradation/bsrgan_light.py:65
↓ 1 callersFunctionanisotropic_Gaussian
generate an anisotropic Gaussian kernel Args: ksize : e.g., 15, kernel size theta : [0, pi], rotation angle range l1
mv-diffusion/One-2-3-45-by-view/ldm/modules/image_degradation/bsrgan.py:65
↓ 1 callersFunctionappend_dims
Appends dimensions to the end of a tensor until it has target_dims dimensions. From https://github.com/crowsonkb/k-diffusion/blob/master/k_diffusi
extern/ldm_zero123/models/diffusion/sampling_util.py:5
↓ 1 callersFunctionappend_dims
Appends dimensions to the end of a tensor until it has target_dims dimensions. From https://github.com/crowsonkb/k-diffusion/blob/master/k_diffusi
mv-diffusion/One-2-3-45-by-view/ldm/models/diffusion/sampling_util.py:5
↓ 1 callersFunctionaugment_img
Kai Zhang (github: https://github.com/cszn)
extern/ldm_zero123/modules/image_degradation/utils_image.py:424
↓ 1 callersFunctionaugment_img
Kai Zhang (github: https://github.com/cszn)
mv-diffusion/One-2-3-45-by-view/ldm/modules/image_degradation/utils_image.py:380
↓ 1 callersFunctionavg_pool_nd
Create a 1D, 2D, or 3D average pooling module.
extern/ldm_zero123/modules/diffusionmodules/util.py:266
↓ 1 callersFunctionavg_pool_nd
Create a 1D, 2D, or 3D average pooling module.
mv-diffusion/MVDream/mvdream/ldm/modules/diffusionmodules/util.py:253
↓ 1 callersFunctionavg_pool_nd
Create a 1D, 2D, or 3D average pooling module.
mv-diffusion/One-2-3-45-by-view/ldm/modules/diffusionmodules/util.py:238
↓ 1 callersMethodbackward
(ctx, g)
threestudio/utils/ops.py:51
↓ 1 callersFunctionbarrier
()
threestudio/utils/misc.py:108
↓ 1 callersFunctionbgr2ycbcr
bgr version of rgb2ycbcr only_y: only return Y channel Input: uint8, [0, 255] float, [0, 1]
extern/ldm_zero123/modules/image_degradation/utils_image.py:626
↓ 1 callersFunctionbgr2ycbcr
bgr version of rgb2ycbcr only_y: only return Y channel Input: uint8, [0, 255] float, [0, 1]
mv-diffusion/One-2-3-45-by-view/ldm/modules/image_degradation/utils_image.py:573
↓ 1 callersFunctionbicubic_interpolate_batch
two dimensional cubic interpolation :param p: [B, N, 4, 4] :param x: [B, N] :param y: [B, N] :return:
mv-diffusion/One-2-3-45-by-view/reconstruction/ops/grid_sampler.py:309
↓ 1 callersFunctionbicubic_interpolate_batch
two dimensional cubic interpolation :param p: [B, N, 4, 4] :param x: [B, N] :param y: [B, N] :return:
mv-diffusion/One-2-3-45/reconstruction/ops/grid_sampler.py:309
↓ 1 callersFunctionbicubic_interpolate_batch
two dimensional cubic interpolation :param p: [B, N, 4, 4] :param x: [B, N] :param y: [B, N] :return:
threestudio/models/geometry/grid_sampler.py:309
↓ 1 callersMethodblend_rgba
(self, img)
mv-diffusion/One-2-3-45-by-view/ldm/data/nerf_like.py:79
↓ 1 callersMethodblend_rgba
(self, img)
mv-diffusion/One-2-3-45-by-view/ldm/data/nerf_like.py:123
↓ 1 callersMethodblend_rgba
(self, img)
mv-diffusion/One-2-3-45-by-view/ldm/data/nerf_like.py:163
↓ 1 callersFunctionbuild_model
(model_name, ckpt_path=None, cache_dir=None)
mv-diffusion/MVDream/mvdream/model_zoo.py:35
↓ 1 callersFunctionbuild_patch_offset
(h_patch_size)
mv-diffusion/One-2-3-45-by-view/reconstruction/models/patch_projector.py:209
↓ 1 callersFunctionbuild_patch_offset
(h_patch_size)
mv-diffusion/One-2-3-45-by-view/reconstruction/models/rays.py:6
↓ 1 callersFunctionbuild_patch_offset
(h_patch_size)
mv-diffusion/One-2-3-45/reconstruction/models/patch_projector.py:209
↓ 1 callersFunctionbuild_patch_offset
(h_patch_size)
mv-diffusion/One-2-3-45/reconstruction/models/rays.py:6
↓ 1 callersMethodcal_scale_mat
(self, img_hw, intrinsics, extrinsics, near_fars, factor=1.)
mv-diffusion/One-2-3-45-by-view/reconstruction/data/One2345_eval_new_data.py:125
↓ 1 callersMethodcal_scale_mat
(self, img_hw, intrinsics, extrinsics, near_fars, factor=1.)
mv-diffusion/One-2-3-45-by-view/reconstruction/data/One2345_train.py:148
↓ 1 callersMethodcal_scale_mat
(self, img_hw, intrinsics, extrinsics, near_fars, factor=1.)
mv-diffusion/One-2-3-45/reconstruction/data/One2345_eval_new_data.py:125
↓ 1 callersMethodcal_scale_mat
(self, img_hw, intrinsics, extrinsics, near_fars, factor=1.)
mv-diffusion/One-2-3-45/reconstruction/data/One2345_train.py:148
↓ 1 callersFunctioncalc_pose
(phis, thetas, size, radius = 1.2, device='cuda')
mv-diffusion/One-2-3-45-by-view/utils/utils.py:80
↓ 1 callersMethodcalculate_adaptive_weight
(self, nll_loss, g_loss, last_layer=None)
extern/ldm_zero123/modules/losses/vqperceptual.py:100
↓ 1 callersMethodcalculate_adaptive_weight
(self, nll_loss, g_loss, last_layer=None)
extern/ldm_zero123/modules/losses/contperceptual.py:40
↓ 1 callersMethodcalculate_adaptive_weight
(self, nll_loss, g_loss, last_layer=None)
mv-diffusion/One-2-3-45-by-view/ldm/modules/losses/vqperceptual.py:85
↓ 1 callersMethodcalculate_adaptive_weight
(self, nll_loss, g_loss, last_layer=None)
mv-diffusion/One-2-3-45-by-view/ldm/modules/losses/contperceptual.py:32
↓ 1 callersMethodcat_z_vals
(self, rays_o, rays_d, z_vals, new_z_vals, sdf, lod, sdf_network, gru_fusion,
mv-diffusion/One-2-3-45-by-view/reconstruction/models/sparse_neus_renderer.py:117
↓ 1 callersMethodcat_z_vals
(self, rays_o, rays_d, z_vals, new_z_vals, sdf, lod, sdf_network, gru_fusion,
mv-diffusion/One-2-3-45/reconstruction/models/sparse_neus_renderer.py:117
↓ 1 callersFunctionce_pq_loss
(p, q, weight=None)
threestudio/utils/ops.py:375
↓ 1 callersMethodcheck_inputs
(self, image, height, width, callback_steps)
extern/zero123.py:353
↓ 1 callersFunctioncheckpoint
Evaluate a function without caching intermediate activations, allowing for reduced memory at the expense of extra compute in the backward pas
threestudio/utils/GAN/network_util.py:125
↓ 1 callersMethodcolor_blend
(self, pts, position, normals, view_dirs, feature_vectors, img_index, pts_pixel_color, pts
mv-diffusion/One-2-3-45-by-view/reconstruction/models/sparse_sdf_network.py:709
↓ 1 callersMethodcolor_blend
(self, pts, position, normals, view_dirs, feature_vectors, img_index, pts_pixel_color, pts
mv-diffusion/One-2-3-45/reconstruction/models/sparse_sdf_network.py:703
↓ 1 callersMethodcompute
extract features of pts for rendering :param pts: :param geometryVolume: :param vol_dims: :param partial_vol_
mv-diffusion/One-2-3-45-by-view/reconstruction/models/projector.py:96
↓ 1 callersMethodcompute
extract features of pts for rendering :param pts: :param geometryVolume: :param vol_dims: :param partial_vol_
mv-diffusion/One-2-3-45/reconstruction/models/projector.py:96
↓ 1 callersMethodcompute_angle
:param xyz: [N_rays, n_samples,3 ] :param query_c2w: [1,4,4] :param supporting_c2ws: [n,4,4] :return:
mv-diffusion/One-2-3-45-by-view/reconstruction/models/projector.py:15
↓ 1 callersMethodcompute_angle
:param xyz: [N_rays, n_samples,3 ] :param query_c2w: [1,4,4] :param supporting_c2ws: [n,4,4] :return:
mv-diffusion/One-2-3-45/reconstruction/models/projector.py:15
↓ 1 callersMethodcompute_angle_view_independent
:param xyz: [N_rays, n_samples,3 ] :param surface_normals: [N_rays, n_samples,3 ] :param supporting_c2ws: [n,4,4] :r
mv-diffusion/One-2-3-45-by-view/reconstruction/models/projector.py:40
↓ 1 callersMethodcompute_angle_view_independent
:param xyz: [N_rays, n_samples,3 ] :param surface_normals: [N_rays, n_samples,3 ] :param supporting_c2ws: [n,4,4] :r
mv-diffusion/One-2-3-45/reconstruction/models/projector.py:40
↓ 1 callersFunctioncompute_frechet_distance
(mu_sample, sigma_sample, mu_ref, sigma_ref)
extern/ldm_zero123/modules/evaluate/torch_frechet_video_distance.py:25
↓ 1 callersFunctioncompute_frechet_distance
(mu_sample,sigma_sample,mu_ref,sigma_ref)
mv-diffusion/One-2-3-45-by-view/ldm/modules/evaluate/torch_frechet_video_distance.py:25
↓ 1 callersMethodcompute_grad_sds
( self, text_embeddings: Float[Tensor, "BB 77 768"], latents: Float[Tensor, "B 4 DH DW
threestudio/models/guidance/controlnet_guidance.py:295
↓ 1 callersMethodcompute_grad_sds
( self, latents: Float[Tensor, "B 4 64 64"], t: Int[Tensor, "B"], prompt_utils
threestudio/models/guidance/stable_diffusion_guidance.py:185
↓ 1 callersMethodcompute_grad_sds
( self, text_embeddings: Float[Tensor, "BB 77 768"], latents: Float[Tensor, "B 4 DH DW
threestudio/models/guidance/instructpix2pix_guidance.py:209
↓ 1 callersMethodcompute_grad_sjc
( self, latents: Float[Tensor, "B 4 64 64"], t: Int[Tensor, "B"], prompt_utils
threestudio/models/guidance/stable_diffusion_guidance.py:278
↓ 1 callersMethodcompute_grad_vsd
( self, latents: Float[Tensor, "B 4 64 64"], text_embeddings_vd: Float[Tensor, "BB 77
threestudio/models/guidance/stable_diffusion_vsd_guidance.py:453
↓ 1 callersMethodcompute_grad_vsd
( self, latents: Float[Tensor, "B 4 64 64"], text_embeddings_vd: Float[Tensor, "BB 77
threestudio/models/guidance/sd_vsd_scale_guidance.py:473
↓ 1 callersMethodcompute_inception_score
( self, activations: np.ndarray, split_size: int = 5000 )
extern/ldm_zero123/modules/evaluate/adm_evaluator.py:210
↓ 1 callersMethodcompute_inception_score
(self, activations: np.ndarray, split_size: int = 5000)
mv-diffusion/One-2-3-45-by-view/ldm/modules/evaluate/adm_evaluator.py:201
↓ 1 callersMethodcompute_loss
(self, inp)
extern/ldm_zero123/guidance.py:20
↓ 1 callersMethodcompute_loss
(self, inp)
mv-diffusion/One-2-3-45-by-view/ldm/guidance.py:19
↓ 1 callersFunctioncompute_perceptual_similarity
(folder, pred_img, tgt_img, take_every_other)
extern/ldm_zero123/modules/evaluate/evaluate_perceptualsim.py:341
↓ 1 callersFunctioncompute_perceptual_similarity
(folder, pred_img, tgt_img, take_every_other)
mv-diffusion/One-2-3-45-by-view/ldm/modules/evaluate/evaluate_perceptualsim.py:353
↓ 1 callersMethodcompute_prec_recall
( self, activations_ref: np.ndarray, activations_sample: np.ndarray )
extern/ldm_zero123/modules/evaluate/adm_evaluator.py:229
↓ 1 callersMethodcompute_prec_recall
( self, activations_ref: np.ndarray, activations_sample: np.ndarray )
mv-diffusion/One-2-3-45-by-view/ldm/modules/evaluate/adm_evaluator.py:216
↓ 1 callersFunctioncompute_statistics
( videos_fake, videos_real, device: str = "cuda", bs=32, only_ref=False, only_sample=F
extern/ldm_zero123/modules/evaluate/torch_frechet_video_distance.py:222
↓ 1 callersFunctioncompute_statistics
(videos_fake, videos_real, device: str='cuda', bs=32, only_ref=False,only_sample=False)
mv-diffusion/One-2-3-45-by-view/ldm/modules/evaluate/torch_frechet_video_distance.py:199
↓ 1 callersMethodcompute_statistics
(self, activations: np.ndarray)
extern/ldm_zero123/modules/evaluate/adm_evaluator.py:205
↓ 1 callersMethodcompute_statistics
(self, activations: np.ndarray)
mv-diffusion/One-2-3-45-by-view/ldm/modules/evaluate/adm_evaluator.py:196
↓ 1 callersMethodcompute_view_independent
extract features of pts for rendering :param pts: :param geometryVolume: :param vol_dims: :param partial_vol_
mv-diffusion/One-2-3-45-by-view/reconstruction/models/projector.py:231
↓ 1 callersMethodconfigure
(self, *args, **kwargs)
threestudio/utils/base.py:85
↓ 1 callersMethodconfigure
(self, *args, **kwargs)
threestudio/utils/base.py:117
↓ 1 callersMethodconfigure
(self)
threestudio/systems/base.py:83
↓ 1 callersFunctionconv_bn
( inp, oup, stride, conv_layer=nn.Conv2d, norm_layer=nn.BatchNorm2d, nlin_layer=nn.ReL
threestudio/utils/GAN/mobilenet.py:8
↓ 1 callersFunctionconvert_from_original_zero123_ckpt
( checkpoint_path, original_config_file, extract_ema, device )
scripts/convert_zero123_to_diffusers.py:871
↓ 1 callersFunctionconvert_from_quartet_to_npz
(quartetfile="cube_32_tet.tet", npzfile="32_tets")
load/tets/generate_tets.py:33
↓ 1 callersFunctionconvert_ldm_unet_checkpoint
Takes a state dict and a config, and returns a converted checkpoint.
scripts/convert_zero123_to_diffusers.py:261
↓ 1 callersFunctionconvert_ldm_vae_checkpoint
(checkpoint, config)
scripts/convert_zero123_to_diffusers.py:634
↓ 1 callersMethodcopy_to
(self, model)
mv-diffusion/MVDream/mvdream/ldm/modules/ema.py:50
↓ 1 callersFunctioncos_sim
(in0, in1)
extern/ldm_zero123/modules/evaluate/evaluate_perceptualsim.py:25
↓ 1 callersFunctioncos_sim
(in0, in1)
mv-diffusion/One-2-3-45-by-view/ldm/modules/evaluate/evaluate_perceptualsim.py:25
↓ 1 callersMethodcreate_embedding_fn
(self)
mv-diffusion/One-2-3-45-by-view/reconstruction/models/embedder.py:12
↓ 1 callersMethodcreate_embedding_fn
(self)
mv-diffusion/One-2-3-45/reconstruction/models/embedder.py:12
↓ 1 callersMethodcreate_from
( other: "BaseGeometry", cfg: Optional[Union[dict, DictConfig]] = None, **kwargs )
threestudio/models/geometry/base.py:43
↓ 1 callersMethodcreate_loggers
(self, cfg_loggers: DictConfig)
threestudio/utils/saving.py:56
↓ 1 callersFunctioncreate_network_with_input_encoding
( n_input_dims: int, n_output_dims: int, encoding_config, network_config )
threestudio/models/networks.py:318
↓ 1 callersFunctioncreate_unet_diffusers_config
Creates a config for the diffusers based on the config of the LDM model.
scripts/convert_zero123_to_diffusers.py:18
↓ 1 callersFunctioncreate_vae_diffusers_config
Creates a config for the diffusers based on the config of the LDM model.
scripts/convert_zero123_to_diffusers.py:610
← previousnext →701–800 of 3,158, ranked by callers