SYMBOL INDEX (656 symbols across 54 files)

FILE: shap_e/diffusion/gaussian_diffusion.py
  function diffusion_from_config (line 14) | def diffusion_from_config(config: Union[str, Dict[str, Any]]) -> "Gaussi...
  function get_beta_schedule (line 45) | def get_beta_schedule(beta_schedule, *, beta_start, beta_end, num_diffus...
  function get_named_beta_schedule (line 59) | def get_named_beta_schedule(schedule_name, num_diffusion_timesteps, **ex...
  function betas_for_alpha_bar (line 102) | def betas_for_alpha_bar(num_diffusion_timesteps, alpha_bar, max_beta=0.9...
  function space_timesteps (line 122) | def space_timesteps(num_timesteps, section_counts):
  class GaussianDiffusion (line 175) | class GaussianDiffusion:
    method __init__ (line 192) | def __init__(
    method get_sigmas (line 246) | def get_sigmas(self, t):
    method q_mean_variance (line 249) | def q_mean_variance(self, x_start, t):
    method q_sample (line 262) | def q_sample(self, x_start, t, noise=None):
    method q_posterior_mean_variance (line 281) | def q_posterior_mean_variance(self, x_start, x_t, t):
    method p_mean_variance (line 305) | def p_mean_variance(
    method _predict_xstart_from_eps (line 400) | def _predict_xstart_from_eps(self, x_t, t, eps):
    method _predict_xstart_from_xprev (line 407) | def _predict_xstart_from_xprev(self, x_t, t, xprev):
    method _predict_eps_from_xstart (line 417) | def _predict_eps_from_xstart(self, x_t, t, pred_xstart):
    method condition_mean (line 422) | def condition_mean(self, cond_fn, p_mean_var, x, t, model_kwargs=None):
    method condition_score (line 435) | def condition_score(self, cond_fn, p_mean_var, x, t, model_kwargs=None):
    method p_sample (line 455) | def p_sample(
    method p_sample_loop (line 499) | def p_sample_loop(
    method p_sample_loop_progressive (line 547) | def p_sample_loop_progressive(
    method ddim_sample (line 598) | def ddim_sample(
    method ddim_reverse_sample (line 648) | def ddim_reverse_sample(
    method ddim_sample_loop (line 686) | def ddim_sample_loop(
    method ddim_sample_loop_progressive (line 722) | def ddim_sample_loop_progressive(
    method _vb_terms_bpd (line 773) | def _vb_terms_bpd(self, model, x_start, x_t, t, clip_denoised=False, m...
    method training_losses (line 810) | def training_losses(
    method _prior_bpd (line 901) | def _prior_bpd(self, x_start):
    method calc_bpd_loop (line 917) | def calc_bpd_loop(self, model, x_start, clip_denoised=False, model_kwa...
    method scale_channels (line 974) | def scale_channels(self, x: th.Tensor) -> th.Tensor:
    method unscale_channels (line 985) | def unscale_channels(self, x: th.Tensor) -> th.Tensor:
    method unscale_out_dict (line 996) | def unscale_out_dict(
  class SpacedDiffusion (line 1004) | class SpacedDiffusion(GaussianDiffusion):
    method __init__ (line 1012) | def __init__(self, use_timesteps: Iterable[int], **kwargs):
    method p_mean_variance (line 1028) | def p_mean_variance(self, model, *args, **kwargs):
    method training_losses (line 1031) | def training_losses(self, model, *args, **kwargs):
    method condition_mean (line 1034) | def condition_mean(self, cond_fn, *args, **kwargs):
    method condition_score (line 1037) | def condition_score(self, cond_fn, *args, **kwargs):
    method _wrap_model (line 1040) | def _wrap_model(self, model):
  class _WrappedModel (line 1046) | class _WrappedModel:
    method __init__ (line 1047) | def __init__(self, model, timestep_map, original_num_steps):
    method __call__ (line 1052) | def __call__(self, x, ts, **kwargs):
  function _extract_into_tensor (line 1058) | def _extract_into_tensor(arr, timesteps, broadcast_shape):
  function normal_kl (line 1074) | def normal_kl(mean1, logvar1, mean2, logvar2):
  function approx_standard_normal_cdf (line 1102) | def approx_standard_normal_cdf(x):
  function discretized_gaussian_log_likelihood (line 1110) | def discretized_gaussian_log_likelihood(x, *, means, log_scales):
  function mean_flat (line 1139) | def mean_flat(tensor):

FILE: shap_e/diffusion/k_diffusion.py
  class KarrasDenoiser (line 31) | class KarrasDenoiser:
    method __init__ (line 32) | def __init__(self, sigma_data: float = 0.5):
    method get_snr (line 35) | def get_snr(self, sigmas):
    method get_sigmas (line 38) | def get_sigmas(self, sigmas):
    method get_scalings (line 41) | def get_scalings(self, sigma):
    method training_losses (line 47) | def training_losses(self, model, x_start, sigmas, model_kwargs=None, n...
    method denoise (line 71) | def denoise(self, model, x_t, sigmas, **model_kwargs):
  class GaussianToKarrasDenoiser (line 79) | class GaussianToKarrasDenoiser:
    method __init__ (line 80) | def __init__(self, model, diffusion):
    method sigma_to_t (line 89) | def sigma_to_t(self, sigma):
    method denoise (line 98) | def denoise(self, x_t, sigmas, clip_denoised=True, model_kwargs=None):
  function karras_sample (line 111) | def karras_sample(*args, **kwargs):
  function karras_sample_progressive (line 118) | def karras_sample_progressive(
  function get_sigmas_karras (line 194) | def get_sigmas_karras(n, sigma_min, sigma_max, rho=7.0, device="cpu"):
  function to_d (line 203) | def to_d(x, sigma, denoised):
  function get_ancestral_step (line 208) | def get_ancestral_step(sigma_from, sigma_to):
  function sample_euler_ancestral (line 217) | def sample_euler_ancestral(model, x, sigmas, progress=False):
  function sample_heun (line 239) | def sample_heun(
  function sample_dpm (line 283) | def sample_dpm(
  function append_dims (line 323) | def append_dims(x, target_dims):
  function append_zero (line 331) | def append_zero(x):

FILE: shap_e/diffusion/sample.py
  function uncond_guide_model (line 15) | def uncond_guide_model(
  function sample_latents (line 31) | def sample_latents(

FILE: shap_e/models/configs.py
  function model_from_config (line 38) | def model_from_config(config: Union[str, Dict[str, Any]], device: torch....

FILE: shap_e/models/download.py
  function default_cache_dir (line 45) | def default_cache_dir() -> str:
  function fetch_file_cached (line 49) | def fetch_file_cached(
  function check_hash (line 85) | def check_hash(path: str, expected_hash: str):
  function hash_file (line 94) | def hash_file(path: str) -> str:
  function load_config (line 105) | def load_config(
  function load_checkpoint (line 122) | def load_checkpoint(
  function load_model (line 139) | def load_model(

FILE: shap_e/models/generation/latent_diffusion.py
  class SplitVectorDiffusion (line 7) | class SplitVectorDiffusion(nn.Module):
    method __init__ (line 8) | def __init__(self, *, device: torch.device, wrapped: nn.Module, n_ctx:...
    method forward (line 18) | def forward(self, x: torch.Tensor, t: torch.Tensor, **kwargs):

FILE: shap_e/models/generation/perceiver.py
  class MultiheadCrossAttention (line 13) | class MultiheadCrossAttention(nn.Module):
    method __init__ (line 14) | def __init__(
    method forward (line 42) | def forward(self, x, data):
  class QKVMultiheadCrossAttention (line 50) | class QKVMultiheadCrossAttention(nn.Module):
    method __init__ (line 51) | def __init__(
    method forward (line 61) | def forward(self, q, kv):
  class ResidualCrossAttentionBlock (line 77) | class ResidualCrossAttentionBlock(nn.Module):
    method __init__ (line 78) | def __init__(
    method forward (line 110) | def forward(self, x: torch.Tensor, data: torch.Tensor):
  class SimplePerceiver (line 116) | class SimplePerceiver(nn.Module):
    method __init__ (line 121) | def __init__(
    method forward (line 155) | def forward(self, x: torch.Tensor, data: torch.Tensor):
  class PointDiffusionPerceiver (line 161) | class PointDiffusionPerceiver(nn.Module):
    method __init__ (line 162) | def __init__(
    method forward (line 224) | def forward(self, x: torch.Tensor, t: torch.Tensor):

FILE: shap_e/models/generation/pooled_mlp.py
  class PooledMLP (line 7) | class PooledMLP(nn.Module):
    method __init__ (line 8) | def __init__(
    method forward (line 32) | def forward(self, x: torch.Tensor, t: torch.Tensor) -> torch.Tensor:
  class ResBlock (line 41) | class ResBlock(nn.Module):
    method __init__ (line 42) | def __init__(self, hidden_size: int, pool_op: str, device: torch.device):
    method forward (line 59) | def forward(self, x: torch.Tensor):
  function pool (line 67) | def pool(op_name: str, x: torch.Tensor) -> torch.Tensor:

FILE: shap_e/models/generation/pretrained_clip.py
  class ImageCLIP (line 13) | class ImageCLIP(nn.Module):
    method __init__ (line 19) | def __init__(
    method feature_dim (line 47) | def feature_dim(self) -> int:
    method grid_size (line 54) | def grid_size(self) -> int:
    method grid_feature_dim (line 61) | def grid_feature_dim(self) -> int:
    method forward (line 67) | def forward(
    method _static_multimodal_embed (line 120) | def _static_multimodal_embed(
    method embed_images (line 159) | def embed_images(self, xs: Iterable[Optional[ImageType]]) -> torch.Ten...
    method embed_text (line 168) | def embed_text(self, prompts: Iterable[str]) -> torch.Tensor:
    method embed_images_grid (line 177) | def embed_images_grid(self, xs: Iterable[Optional[ImageType]]) -> torc...
    method images_to_tensor (line 215) | def images_to_tensor(self, xs: Iterable[Optional[ImageType]]) -> torch...
  class FrozenImageCLIP (line 219) | class FrozenImageCLIP:
    method __init__ (line 220) | def __init__(self, device: torch.device, **kwargs):
    method feature_dim (line 226) | def feature_dim(self) -> int:
    method grid_size (line 230) | def grid_size(self) -> int:
    method grid_feature_dim (line 234) | def grid_feature_dim(self) -> int:
    method __call__ (line 237) | def __call__(
    method embed_images (line 249) | def embed_images(self, xs: Iterable[Optional[ImageType]]) -> torch.Ten...
    method embed_text (line 253) | def embed_text(self, prompts: Iterable[str]) -> torch.Tensor:
    method embed_images_grid (line 257) | def embed_images_grid(self, xs: Iterable[Optional[ImageType]]) -> torc...
  function _image_to_pil (line 262) | def _image_to_pil(obj: Optional[ImageType]) -> Image.Image:

FILE: shap_e/models/generation/transformer.py
  function init_linear (line 13) | def init_linear(l, stddev):
  class MultiheadAttention (line 19) | class MultiheadAttention(nn.Module):
    method __init__ (line 20) | def __init__(
    method forward (line 40) | def forward(self, x):
  class MLP (line 47) | class MLP(nn.Module):
    method __init__ (line 48) | def __init__(self, *, device: torch.device, dtype: torch.dtype, width:...
    method forward (line 57) | def forward(self, x):
  class QKVMultiheadAttention (line 61) | class QKVMultiheadAttention(nn.Module):
    method __init__ (line 62) | def __init__(self, *, device: torch.device, dtype: torch.dtype, heads:...
    method forward (line 69) | def forward(self, qkv):
  class ResidualAttentionBlock (line 83) | class ResidualAttentionBlock(nn.Module):
    method __init__ (line 84) | def __init__(
    method forward (line 108) | def forward(self, x: torch.Tensor):
  class Transformer (line 114) | class Transformer(nn.Module):
    method __init__ (line 115) | def __init__(
    method forward (line 145) | def forward(self, x: torch.Tensor):
  class PointDiffusionTransformer (line 151) | class PointDiffusionTransformer(nn.Module):
    method __init__ (line 152) | def __init__(
    method forward (line 203) | def forward(self, x: torch.Tensor, t: torch.Tensor):
    method _forward_with_cond (line 213) | def _forward_with_cond(
  class CLIPImagePointDiffusionTransformer (line 239) | class CLIPImagePointDiffusionTransformer(PointDiffusionTransformer):
    method __init__ (line 240) | def __init__(
    method cached_model_kwargs (line 262) | def cached_model_kwargs(self, batch_size: int, model_kwargs: Dict[str,...
    method forward (line 266) | def forward(
  class CLIPImageGridPointDiffusionTransformer (line 301) | class CLIPImageGridPointDiffusionTransformer(PointDiffusionTransformer):
    method __init__ (line 302) | def __init__(
    method cached_model_kwargs (line 330) | def cached_model_kwargs(self, batch_size: int, model_kwargs: Dict[str,...
    method forward (line 335) | def forward(
  class UpsamplePointDiffusionTransformer (line 371) | class UpsamplePointDiffusionTransformer(PointDiffusionTransformer):
    method __init__ (line 372) | def __init__(
    method forward (line 404) | def forward(self, x: torch.Tensor, t: torch.Tensor, *, low_res: torch....
    method _embed_low_res (line 417) | def _embed_low_res(self, x: torch.Tensor) -> torch.Tensor:
  class CLIPImageGridUpsamplePointDiffusionTransformer (line 425) | class CLIPImageGridUpsamplePointDiffusionTransformer(UpsamplePointDiffus...
    method __init__ (line 426) | def __init__(
    method cached_model_kwargs (line 449) | def cached_model_kwargs(self, batch_size: int, model_kwargs: Dict[str,...
    method forward (line 457) | def forward(

FILE: shap_e/models/generation/util.py
  function timestep_embedding (line 6) | def timestep_embedding(timesteps, dim, max_period=10000):

FILE: shap_e/models/nerf/model.py
  class NeRFModel (line 18) | class NeRFModel(ABC):
    method forward (line 24) | def forward(
  class VoidNeRFModel (line 41) | class VoidNeRFModel(MetaModule, NeRFModel):
    method __init__ (line 47) | def __init__(
    method forward (line 64) | def forward(
  class MLPNeRFModel (line 83) | class MLPNeRFModel(MetaModule, NeRFModel):
    method __init__ (line 84) | def __init__(
    method encode_position (line 170) | def encode_position(self, query: Query):
    method forward (line 174) | def forward(
  function maybe_get_spherical_harmonics_basis (line 241) | def maybe_get_spherical_harmonics_basis(

FILE: shap_e/models/nerf/ray.py
  function render_rays (line 15) | def render_rays(
  class RayVolumeIntegralResults (line 133) | class RayVolumeIntegralResults:
    method combine (line 162) | def combine(self, cur: "RayVolumeIntegralResults") -> "RayVolumeIntegr...
  class RayVolumeIntegral (line 208) | class RayVolumeIntegral:
    method render_rays (line 214) | def render_rays(
    method integrate_samples (line 297) | def integrate_samples(
    method _merge_results (line 381) | def _merge_results(
  class RaySampler (line 399) | class RaySampler(ABC):
    method sample (line 401) | def sample(self, t0: torch.Tensor, t1: torch.Tensor, n_samples: int) -...
  class StratifiedRaySampler (line 410) | class StratifiedRaySampler(RaySampler):
    method __init__ (line 416) | def __init__(self, depth_mode: str = "linear"):
    method sample (line 424) | def sample(
  class ImportanceRaySampler (line 459) | class ImportanceRaySampler(RaySampler):
    method __init__ (line 465) | def __init__(
    method sample (line 485) | def sample(self, t0: torch.Tensor, t1: torch.Tensor, n_samples: int) -...

FILE: shap_e/models/nerf/renderer.py
  class TwoStepNeRFRenderer (line 15) | class TwoStepNeRFRenderer(RayRenderer):
    method __init__ (line 21) | def __init__(
    method render_rays (line 69) | def render_rays(
  class OneStepNeRFRenderer (line 199) | class OneStepNeRFRenderer(RayRenderer):
    method __init__ (line 205) | def __init__(
    method render_rays (line 232) | def render_rays(

FILE: shap_e/models/nerstf/mlp.py
  class MLPDensitySDFModel (line 11) | class MLPDensitySDFModel(MLPModel):
    method __init__ (line 12) | def __init__(
    method forward (line 28) | def forward(
  class MLPNeRSTFModel (line 45) | class MLPNeRSTFModel(MLPModel):
    method __init__ (line 46) | def __init__(
    method forward (line 82) | def forward(
  function indices_for_output_mode (line 117) | def indices_for_output_mode(
  function map_indices_to_keys (line 168) | def map_indices_to_keys(mapping: IndexMapping, data: torch.Tensor) -> At...
  function index_mapping_max (line 172) | def index_mapping_max(mapping: IndexMapping) -> int:

FILE: shap_e/models/nerstf/renderer.py
  class NeRSTFRenderer (line 19) | class NeRSTFRenderer(RayRenderer, STFRendererBase):
    method __init__ (line 20) | def __init__(
    method _query (line 63) | def _query(
    method render_rays (line 92) | def render_rays(
    method render_views (line 185) | def render_views(
    method get_signed_distance (line 269) | def get_signed_distance(
    method get_texture (line 280) | def get_texture(

FILE: shap_e/models/nn/camera.py
  class DifferentiableCamera (line 12) | class DifferentiableCamera(ABC):
    method camera_rays (line 18) | def camera_rays(self, coords: torch.Tensor) -> torch.Tensor:
    method resize_image (line 29) | def resize_image(self, width: int, height: int) -> "DifferentiableCame...
  class DifferentiableProjectiveCamera (line 37) | class DifferentiableProjectiveCamera(DifferentiableCamera):
    method __post_init__ (line 51) | def __post_init__(self):
    method resolution (line 62) | def resolution(self):
    method fov (line 65) | def fov(self):
    method image_coords (line 68) | def image_coords(self) -> torch.Tensor:
    method camera_rays (line 82) | def camera_rays(self, coords: torch.Tensor) -> torch.Tensor:
    method resize_image (line 112) | def resize_image(self, width: int, height: int) -> "DifferentiableProj...
  class DifferentiableCameraBatch (line 130) | class DifferentiableCameraBatch(ABC):
  function normalize (line 139) | def normalize(vec: torch.Tensor) -> torch.Tensor:
  function project_out (line 143) | def project_out(vec1: torch.Tensor, vec2: torch.Tensor) -> torch.Tensor:
  function camera_orientation (line 152) | def camera_orientation(toward: torch.Tensor, up: Optional[torch.Tensor] ...
  function projective_camera_frame (line 175) | def projective_camera_frame(
  function get_image_coords (line 202) | def get_image_coords(width, height) -> torch.Tensor:

FILE: shap_e/models/nn/checkpoint.py
  function checkpoint (line 7) | def checkpoint(
  class CheckpointFunction (line 29) | class CheckpointFunction(torch.autograd.Function):
    method forward (line 32) | def forward(ctx, run_function, length, *args):
    method backward (line 44) | def backward(ctx, *output_grads):
  class CheckpointFunctionGradFunction (line 59) | class CheckpointFunctionGradFunction(torch.autograd.Function):
    method forward (line 62) | def forward(ctx, run_function, length_1, length_2, *args):
    method backward (line 87) | def backward(ctx, *all_output_grads):

FILE: shap_e/models/nn/encoding.py
  function encode_position (line 9) | def encode_position(version: str, *, position: torch.Tensor):
  function encode_channels (line 20) | def encode_channels(version: str, *, channels: torch.Tensor):
  function position_encoding_channels (line 31) | def position_encoding_channels(version: Optional[str] = None) -> int:
  function channel_encoding_channels (line 37) | def channel_encoding_channels(version: Optional[str] = None) -> int:
  class PosEmbLinear (line 43) | class PosEmbLinear(nn.Linear):
    method __init__ (line 44) | def __init__(
    method forward (line 54) | def forward(self, x: torch.Tensor):
  class MultiviewPoseEmbedding (line 60) | class MultiviewPoseEmbedding(nn.Conv2d):
    method __init__ (line 61) | def __init__(
    method forward (line 84) | def forward(
  class MultiviewPointCloudEmbedding (line 116) | class MultiviewPointCloudEmbedding(nn.Conv2d):
    method __init__ (line 117) | def __init__(
    method forward (line 144) | def forward(
  function maybe_encode_direction (line 180) | def maybe_encode_direction(
  function posenc_nerf (line 200) | def posenc_nerf(x: torch.Tensor, min_deg: int = 0, max_deg: int = 15) ->...
  function get_scales (line 217) | def get_scales(
  function spherical_harmonics_basis (line 226) | def spherical_harmonics_basis(

FILE: shap_e/models/nn/meta.py
  function subdict (line 46) | def subdict(dictionary, key=None):
  function superdict (line 61) | def superdict(dictionary, key=None):
  function leveldict (line 69) | def leveldict(dictionary, depth=0):
  function leveliter (line 73) | def leveliter(dictionary, depth=0):
  class MetaModule (line 82) | class MetaModule(nn.Module):
    method __init__ (line 103) | def __init__(self, *args, **kwargs):
    method register_meta_buffer (line 108) | def register_meta_buffer(self, name: str, param: nn.Parameter):
    method register_meta_parameter (line 116) | def register_meta_parameter(self, name: str, parameter: nn.Parameter):
    method register_meta (line 125) | def register_meta(self, name: str, parameter: nn.Parameter, trainable:...
    method register (line 131) | def register(self, name: str, parameter: nn.Parameter, meta: bool, tra...
    method named_meta_parameters (line 143) | def named_meta_parameters(self, prefix="", recurse=True):
    method named_nonmeta_parameters (line 162) | def named_nonmeta_parameters(self, prefix="", recurse=True):
    method nonmeta_parameters (line 177) | def nonmeta_parameters(self, prefix="", recurse=True):
    method meta_state_dict (line 181) | def meta_state_dict(self, prefix="", recurse=True):
    method update (line 203) | def update(self, params=None):
  function batch_meta_parameters (line 221) | def batch_meta_parameters(net, batch_size):
  function batch_meta_state_dict (line 228) | def batch_meta_state_dict(net, batch_size):

FILE: shap_e/models/nn/ops.py
  function gelu (line 15) | def gelu(x):
  function swish (line 19) | def swish(x):
  function quick_gelu (line 23) | def quick_gelu(x):
  function torch_gelu (line 27) | def torch_gelu(x):
  function geglu (line 31) | def geglu(x):
  class SirenSin (line 36) | class SirenSin:
    method __init__ (line 37) | def __init__(self, w0=30.0):
    method __call__ (line 40) | def __call__(self, x):
  function get_act (line 44) | def get_act(name):
  function zero_init (line 64) | def zero_init(affine):
  function siren_init_first_layer (line 70) | def siren_init_first_layer(affine, init_scale: float = 1.0):
  function siren_init (line 78) | def siren_init(affine, coeff=1.0, init_scale: float = 1.0):
  function siren_init_30 (line 86) | def siren_init_30(affine, init_scale: float = 1.0):
  function std_init (line 90) | def std_init(affine, init_scale: float = 1.0):
  function mlp_init (line 98) | def mlp_init(affines, init: Optional[str] = None, init_scale: float = 1.0):
  class MetaLinear (line 114) | class MetaLinear(MetaModule):
    method __init__ (line 115) | def __init__(
    method reset_parameters (line 148) | def reset_parameters(self) -> None:
    method _bcast (line 161) | def _bcast(self, op, left, right):
    method forward (line 167) | def forward(self, x, params=None):
  function Conv (line 191) | def Conv(n_dim, d_in, d_out, kernel, stride=1, padding=0, dilation=1, **...
  function flatten (line 200) | def flatten(x):
  function unflatten (line 208) | def unflatten(x, info):
  function torchify (line 213) | def torchify(x):
  function untorchify (line 218) | def untorchify(x):
  class MLP (line 223) | class MLP(nn.Module):
    method __init__ (line 224) | def __init__(
    method forward (line 251) | def forward(self, h, options: Optional[AttrDict] = None, log_prefix: s...
  class MetaMLP (line 260) | class MetaMLP(MetaModule):
    method __init__ (line 261) | def __init__(
    method forward (line 300) | def forward(self, h, params=None, options: Optional[AttrDict] = None, ...
  class LayerNorm (line 311) | class LayerNorm(nn.LayerNorm):
    method __init__ (line 312) | def __init__(
    method forward (line 319) | def forward(self, input):
  class PointSetEmbedding (line 328) | class PointSetEmbedding(nn.Module):
    method __init__ (line 329) | def __init__(
    method forward (line 370) | def forward(self, xyz, points):
    method apply_conv (line 403) | def apply_conv(self, points: torch.Tensor, conv: nn.Module):

FILE: shap_e/models/nn/pointnet2_utils.py
  function timeit (line 35) | def timeit(tag, t):
  function pc_normalize (line 40) | def pc_normalize(pc):
  function square_distance (line 49) | def square_distance(src, dst):
  function index_points (line 73) | def index_points(points, idx):
  function farthest_point_sample (line 95) | def farthest_point_sample(xyz, npoint, deterministic=False):
  function query_ball_point (line 122) | def query_ball_point(radius, nsample, xyz, new_xyz):
  function sample_and_group (line 145) | def sample_and_group(
  function sample_and_group_all (line 192) | def sample_and_group_all(xyz, points):
  class PointNetSetAbstraction (line 212) | class PointNetSetAbstraction(nn.Module):
    method __init__ (line 213) | def __init__(self, npoint, radius, nsample, in_channel, mlp, group_all):
    method forward (line 227) | def forward(self, xyz, points):
  class PointNetSetAbstractionMsg (line 258) | class PointNetSetAbstractionMsg(nn.Module):
    method __init__ (line 259) | def __init__(self, npoint, radius_list, nsample_list, in_channel, mlp_...
    method forward (line 277) | def forward(self, xyz, points):
  class PointNetFeaturePropagation (line 318) | class PointNetFeaturePropagation(nn.Module):
    method __init__ (line 319) | def __init__(self, in_channel, mlp):
    method forward (line 329) | def forward(self, xyz1, xyz2, points1, points2):

FILE: shap_e/models/nn/utils.py
  function to_torch (line 9) | def to_torch(arr: ArrayType, dtype=torch.float):
  function sample_pmf (line 15) | def sample_pmf(pmf: torch.Tensor, n_samples: int) -> torch.Tensor:
  function safe_divide (line 36) | def safe_divide(a, b, epsilon=1e-6):

FILE: shap_e/models/query.py
  class Query (line 8) | class Query:
    method copy (line 16) | def copy(self) -> "Query":
    method map_tensors (line 24) | def map_tensors(self, f: Callable[[torch.Tensor], torch.Tensor]) -> "Q...

FILE: shap_e/models/renderer.py
  class Renderer (line 17) | class Renderer(MetaModule):
    method render_views (line 25) | def render_views(
  class RayRenderer (line 55) | class RayRenderer(Renderer):
    method render_rays (line 63) | def render_rays(
    method render_views (line 76) | def render_views(
    method forward (line 92) | def forward(
  function get_camera_from_batch (line 146) | def get_camera_from_batch(batch: AttrDict) -> Tuple[DifferentiableCamera...
  function append_tensor (line 166) | def append_tensor(val_list: Optional[List[torch.Tensor]], output: Option...
  function render_views_from_rays (line 172) | def render_views_from_rays(

FILE: shap_e/models/stf/base.py
  class Model (line 11) | class Model(ABC):
    method forward (line 13) | def forward(
    method forward_batched (line 23) | def forward_batched(

FILE: shap_e/models/stf/mlp.py
  class MLPModel (line 17) | class MLPModel(MetaModule, Model):
    method __init__ (line 18) | def __init__(
    method forward (line 107) | def forward(
    method _run_mlp (line 125) | def _run_mlp(
    method _mlp (line 152) | def _mlp(
  class MLPSDFModel (line 183) | class MLPSDFModel(MLPModel):
    method __init__ (line 184) | def __init__(self, initial_bias: float = -0.1, **kwargs):
    method forward (line 188) | def forward(
  class MLPTextureFieldModel (line 198) | class MLPTextureFieldModel(MLPModel):
    method __init__ (line 199) | def __init__(
    method forward (line 206) | def forward(

FILE: shap_e/models/stf/renderer.py
  class STFRendererBase (line 25) | class STFRendererBase(ABC):
    method get_signed_distance (line 27) | def get_signed_distance(
    method get_texture (line 36) | def get_texture(
  class STFRenderer (line 45) | class STFRenderer(Renderer, STFRendererBase):
    method __init__ (line 46) | def __init__(
    method render_views (line 76) | def render_views(
    method get_signed_distance (line 106) | def get_signed_distance(
    method get_texture (line 118) | def get_texture(
  function render_views_from_stf (line 131) | def render_views_from_stf(
  function _render_with_pytorch3d (line 315) | def _render_with_pytorch3d(
  function _render_with_raycast (line 387) | def _render_with_raycast(
  function _convert_srgb_to_linear (line 458) | def _convert_srgb_to_linear(u: torch.Tensor) -> torch.Tensor:
  function _convert_linear_to_srgb (line 462) | def _convert_linear_to_srgb(u: torch.Tensor) -> torch.Tensor:
  function cross_entropy_sdf_loss (line 466) | def cross_entropy_sdf_loss(fields: torch.Tensor):
  function slice_fields (line 484) | def slice_fields(fields: torch.Tensor, dim: int, start: int, end: int):
  function volume_query_points (line 495) | def volume_query_points(

FILE: shap_e/models/transmitter/base.py
  class Encoder (line 14) | class Encoder(nn.Module, ABC):
    method __init__ (line 15) | def __init__(self, *, device: torch.device, param_shapes: Dict[str, Tu...
    method forward (line 26) | def forward(self, batch: AttrDict, options: Optional[AttrDict] = None)...
  class VectorEncoder (line 32) | class VectorEncoder(Encoder):
    method __init__ (line 33) | def __init__(
    method forward (line 57) | def forward(self, batch: AttrDict, options: Optional[AttrDict] = None)...
    method encode_to_bottleneck (line 61) | def encode_to_bottleneck(
    method encode_to_vector (line 70) | def encode_to_vector(self, batch: AttrDict, options: Optional[AttrDict...
    method bottleneck_to_params (line 75) | def bottleneck_to_params(
  class ChannelsEncoder (line 82) | class ChannelsEncoder(VectorEncoder):
    method __init__ (line 83) | def __init__(
    method encode_to_channels (line 105) | def encode_to_channels(
    method encode_to_vector (line 113) | def encode_to_vector(self, batch: AttrDict, options: Optional[AttrDict...
    method bottleneck_to_channels (line 116) | def bottleneck_to_channels(
    method bottleneck_to_params (line 122) | def bottleneck_to_params(
  class Transmitter (line 131) | class Transmitter(nn.Module):
    method __init__ (line 132) | def __init__(self, encoder: Encoder, renderer: Renderer):
    method forward (line 137) | def forward(self, batch: AttrDict, options: Optional[AttrDict] = None)...
  class VectorDecoder (line 145) | class VectorDecoder(nn.Module):
    method __init__ (line 146) | def __init__(
    method bottleneck_to_params (line 169) | def bottleneck_to_params(
  class ChannelsDecoder (line 176) | class ChannelsDecoder(VectorDecoder):
    method __init__ (line 177) | def __init__(
    method bottleneck_to_channels (line 186) | def bottleneck_to_channels(
    method bottleneck_to_params (line 192) | def bottleneck_to_params(

FILE: shap_e/models/transmitter/bottleneck.py
  class LatentBottleneck (line 12) | class LatentBottleneck(nn.Module, ABC):
    method __init__ (line 13) | def __init__(self, *, device: torch.device, d_latent: int):
    method forward (line 19) | def forward(self, x: torch.Tensor, options: Optional[AttrDict] = None)...
  class LatentWarp (line 23) | class LatentWarp(nn.Module, ABC):
    method __init__ (line 24) | def __init__(self, *, device: torch.device):
    method warp (line 29) | def warp(self, x: torch.Tensor, options: Optional[AttrDict] = None) ->...
    method unwarp (line 33) | def unwarp(self, x: torch.Tensor, options: Optional[AttrDict] = None) ...
  class IdentityLatentWarp (line 37) | class IdentityLatentWarp(LatentWarp):
    method warp (line 38) | def warp(self, x: torch.Tensor, options: Optional[AttrDict] = None) ->...
    method unwarp (line 42) | def unwarp(self, x: torch.Tensor, options: Optional[AttrDict] = None) ...
  class Tan2LatentWarp (line 47) | class Tan2LatentWarp(LatentWarp):
    method __init__ (line 48) | def __init__(self, *, coeff1: float = 1.0, device: torch.device):
    method warp (line 53) | def warp(self, x: torch.Tensor, options: Optional[AttrDict] = None) ->...
    method unwarp (line 57) | def unwarp(self, x: torch.Tensor, options: Optional[AttrDict] = None) ...
  class IdentityLatentBottleneck (line 62) | class IdentityLatentBottleneck(LatentBottleneck):
    method forward (line 63) | def forward(self, x: torch.Tensor, options: Optional[AttrDict] = None)...
  class ClampNoiseBottleneck (line 68) | class ClampNoiseBottleneck(LatentBottleneck):
    method __init__ (line 69) | def __init__(self, *, device: torch.device, d_latent: int, noise_scale...
    method forward (line 73) | def forward(self, x: torch.Tensor, options: Optional[AttrDict] = None)...
  class ClampDiffusionNoiseBottleneck (line 81) | class ClampDiffusionNoiseBottleneck(LatentBottleneck):
    method __init__ (line 82) | def __init__(
    method forward (line 94) | def forward(self, x: torch.Tensor, options: Optional[AttrDict] = None)...
  function latent_bottleneck_from_config (line 106) | def latent_bottleneck_from_config(config: Dict[str, Any], device: torch....
  function latent_warp_from_config (line 118) | def latent_warp_from_config(config: Dict[str, Any], device: torch.device):

FILE: shap_e/models/transmitter/channels_encoder.py
  class TransformerChannelsEncoder (line 29) | class TransformerChannelsEncoder(ChannelsEncoder, ABC):
    method __init__ (line 35) | def __init__(
    method encode_input (line 85) | def encode_input(self, batch: AttrDict, options: Optional[AttrDict] = ...
    method encode_to_channels (line 88) | def encode_to_channels(
  class PerceiverChannelsEncoder (line 101) | class PerceiverChannelsEncoder(ChannelsEncoder, ABC):
    method __init__ (line 107) | def __init__(
    method get_h_and_iterator (line 180) | def get_h_and_iterator(
    method encode_to_channels (line 190) | def encode_to_channels(
    method get_n_unrolls (line 208) | def get_n_unrolls(self):
  class DatasetIterator (line 221) | class DatasetIterator:
    method __iter__ (line 226) | def __iter__(self):
    method __next__ (line 230) | def __next__(self):
    method _reset (line 243) | def _reset(self):
    method _shuffle (line 247) | def _shuffle(self):
  class PointCloudTransformerChannelsEncoder (line 261) | class PointCloudTransformerChannelsEncoder(TransformerChannelsEncoder):
    method __init__ (line 267) | def __init__(
    method encode_input (line 279) | def encode_input(self, batch: AttrDict, options: Optional[AttrDict] = ...
  class PointCloudPerceiverChannelsEncoder (line 286) | class PointCloudPerceiverChannelsEncoder(PerceiverChannelsEncoder):
    method __init__ (line 292) | def __init__(
    method get_h_and_iterator (line 464) | def get_h_and_iterator(
    method sample_pcl_fps (line 501) | def sample_pcl_fps(self, points: torch.Tensor) -> torch.Tensor:
    method get_pcl_dataset (line 504) | def get_pcl_dataset(
    method get_multiview_dataset (line 518) | def get_multiview_dataset(
    method get_dense_pose_multiview_dataset (line 545) | def get_dense_pose_multiview_dataset(
    method get_pcl_and_multiview_pcl_dataset (line 572) | def get_pcl_and_multiview_pcl_dataset(
    method get_multiview_pcl_dataset (line 606) | def get_multiview_pcl_dataset(
    method encode_views (line 638) | def encode_views(self, batch: AttrDict) -> torch.Tensor:
    method encode_dense_pose_views (line 669) | def encode_dense_pose_views(self, batch: AttrDict) -> torch.Tensor:
    method encode_multiview_pcl (line 696) | def encode_multiview_pcl(self, batch: AttrDict, use_distance: bool = T...
    method views_to_tensor (line 728) | def views_to_tensor(self, views: Union[torch.Tensor, List[List[Image.I...
    method depths_to_tensor (line 750) | def depths_to_tensor(
    method view_alphas_to_tensor (line 776) | def view_alphas_to_tensor(
    method raw_depths_to_tensor (line 804) | def raw_depths_to_tensor(
    method cameras_to_tensor (line 829) | def cameras_to_tensor(
    method dense_pose_cameras_to_tensor (line 855) | def dense_pose_cameras_to_tensor(
  function sample_pcl_fps (line 916) | def sample_pcl_fps(points: torch.Tensor, data_ctx: int, method: str = "f...
  function sample_fps (line 939) | def sample_fps(example: torch.Tensor, n_samples: int) -> torch.Tensor:

FILE: shap_e/models/transmitter/multiview_encoder.py
  class MultiviewTransformerEncoder (line 16) | class MultiviewTransformerEncoder(VectorEncoder):
    method __init__ (line 22) | def __init__(
    method encode_to_vector (line 99) | def encode_to_vector(self, batch: AttrDict, options: Optional[AttrDict...
    method views_to_tensor (line 131) | def views_to_tensor(self, views: Union[torch.Tensor, List[List[Image.I...
    method depths_to_tensor (line 152) | def depths_to_tensor(
    method cameras_to_tensor (line 177) | def cameras_to_tensor(

FILE: shap_e/models/transmitter/params_proj.py
  function flatten_param_shapes (line 13) | def flatten_param_shapes(param_shapes: Dict[str, Tuple[int]]):
  class ParamsProj (line 21) | class ParamsProj(nn.Module, ABC):
    method __init__ (line 22) | def __init__(self, *, device: torch.device, param_shapes: Dict[str, Tu...
    method forward (line 29) | def forward(self, x: torch.Tensor, options: Optional[AttrDict] = None)...
  class LinearParamsProj (line 33) | class LinearParamsProj(ParamsProj):
    method __init__ (line 34) | def __init__(
    method forward (line 55) | def forward(self, x: torch.Tensor, options: Optional[AttrDict] = None)...
  class MLPParamsProj (line 63) | class MLPParamsProj(ParamsProj):
    method __init__ (line 64) | def __init__(
    method forward (line 84) | def forward(self, x: torch.Tensor, options: Optional[AttrDict] = None)...
  class ChannelsProj (line 92) | class ChannelsProj(nn.Module):
    method __init__ (line 93) | def __init__(
    method forward (line 125) | def forward(self, x: torch.Tensor) -> torch.Tensor:
  class ChannelsParamsProj (line 138) | class ChannelsParamsProj(ParamsProj):
    method __init__ (line 139) | def __init__(
    method forward (line 166) | def forward(self, x: torch.Tensor, options: Optional[AttrDict] = None)...
  function params_proj_from_config (line 178) | def params_proj_from_config(
  function _sanitize_name (line 196) | def _sanitize_name(x: str) -> str:

FILE: shap_e/models/transmitter/pc_encoder.py
  class PointCloudTransformerEncoder (line 21) | class PointCloudTransformerEncoder(VectorEncoder):
    method __init__ (line 27) | def __init__(
    method encode_to_vector (line 77) | def encode_to_vector(self, batch: AttrDict, options: Optional[AttrDict...
  class PerceiverEncoder (line 90) | class PerceiverEncoder(VectorEncoder):
    method __init__ (line 96) | def __init__(
    method get_h_and_iterator (line 162) | def get_h_and_iterator(
    method encode_to_vector (line 172) | def encode_to_vector(self, batch: AttrDict, options: Optional[AttrDict...
    method get_n_unrolls (line 184) | def get_n_unrolls(self):
  class PointCloudPerceiverEncoder (line 196) | class PointCloudPerceiverEncoder(PerceiverEncoder):
    method __init__ (line 202) | def __init__(
    method get_h_and_iterator (line 262) | def get_h_and_iterator(
    method sample_pcl_fps (line 291) | def sample_pcl_fps(self, points: torch.Tensor) -> torch.Tensor:
    method get_pcl_dataset (line 294) | def get_pcl_dataset(
    method get_multiview_dataset (line 302) | def get_multiview_dataset(
    method encode_views (line 323) | def encode_views(self, batch: AttrDict) -> torch.Tensor:
    method views_to_tensor (line 354) | def views_to_tensor(self, views: Union[torch.Tensor, List[List[Image.I...
    method depths_to_tensor (line 376) | def depths_to_tensor(
    method cameras_to_tensor (line 402) | def cameras_to_tensor(

FILE: shap_e/models/volume.py
  class VolumeRange (line 12) | class VolumeRange:
    method __post_init__ (line 17) | def __post_init__(self):
    method next_t0 (line 20) | def next_t0(self):
    method extend (line 28) | def extend(self, another: "VolumeRange") -> "VolumeRange":
    method partition (line 39) | def partition(self, ts) -> Tuple[torch.Tensor, torch.Tensor, torch.Ten...
  class Volume (line 61) | class Volume(ABC):
    method intersect (line 67) | def intersect(
  class BoundingBoxVolume (line 89) | class BoundingBoxVolume(MetaModule, Volume):
    method __init__ (line 94) | def __init__(
    method intersect (line 120) | def intersect(
  class UnboundedVolume (line 169) | class UnboundedVolume(MetaModule, Volume):
    method __init__ (line 176) | def __init__(
    method intersect (line 192) | def intersect(
  class SphericalVolume (line 221) | class SphericalVolume(MetaModule, Volume):
    method __init__ (line 227) | def __init__(
    method intersect (line 246) | def intersect(

FILE: shap_e/rendering/blender/blender_script.py
  function clear_scene (line 29) | def clear_scene():
  function clear_lights (line 34) | def clear_lights():
  function import_model (line 42) | def import_model(path):
  function scene_root_objects (line 62) | def scene_root_objects():
  function scene_bbox (line 68) | def scene_bbox(single_obj=None, ignore_matrix=False):
  function scene_meshes (line 85) | def scene_meshes():
  function normalize_scene (line 91) | def normalize_scene():
  function create_camera (line 119) | def create_camera():
  function set_camera (line 127) | def set_camera(direction, camera_dist=2.0):
  function randomize_camera (line 138) | def randomize_camera(camera_dist=2.0):
  function pan_camera (line 143) | def pan_camera(time, axis="Z", camera_dist=2.0, elevation=0.1):
  function place_camera (line 155) | def place_camera(time, camera_pose_mode="random", camera_dist_min=2.0, c...
  function create_light (line 167) | def create_light(location, energy=1.0, angle=0.5 * math.pi / 180):
  function create_random_lights (line 183) | def create_random_lights(count=4, distance=2.0, energy=1.5):
  function create_camera_light (line 189) | def create_camera_light():
  function create_uniform_light (line 194) | def create_uniform_light(backend):
  function create_vertex_color_shaders (line 203) | def create_vertex_color_shaders():
  function create_default_materials (line 249) | def create_default_materials():
  function find_materials (line 258) | def find_materials():
  function delete_all_materials (line 268) | def delete_all_materials():
  function setup_material_extraction_shaders (line 275) | def setup_material_extraction_shaders(capturing_material_alpha: bool):
  function setup_material_extraction_shader_for_material (line 291) | def setup_material_extraction_shader_for_material(mat, capturing_materia...
  function get_socket_value (line 346) | def get_socket_value(tree, socket):
  function clear_socket_input (line 356) | def clear_socket_input(tree, socket):
  function set_socket_value (line 362) | def set_socket_value(tree, socket, socket_and_default):
  function setup_nodes (line 374) | def setup_nodes(output_path, capturing_material_alpha: bool = False, bas...
  function render_scene (line 469) | def render_scene(output_path, fast_mode: bool, extract_material: bool, b...
  function scene_fov (line 538) | def scene_fov():
  function write_camera_metadata (line 550) | def write_camera_metadata(path):
  function save_rendering_dataset (line 571) | def save_rendering_dataset(
  function main (line 638) | def main():

FILE: shap_e/rendering/blender/render.py
  function render_model (line 18) | def render_model(
  function render_mesh (line 100) | def render_mesh(
  function _combine_rgba (line 119) | def _combine_rgba(out_dir: str):
  function _blender_binary_path (line 134) | def _blender_binary_path() -> str:

FILE: shap_e/rendering/blender/view_data.py
  class BlenderViewData (line 12) | class BlenderViewData(ViewData):
    method __init__ (line 17) | def __init__(self, f_obj: BinaryIO):
    method num_views (line 35) | def num_views(self) -> int:
    method channel_names (line 39) | def channel_names(self) -> List[str]:
    method load_view (line 42) | def load_view(self, index: int, channels: List[str]) -> Tuple[Camera, ...
    method camera (line 73) | def camera(self, index: int, width: int, height: int) -> ProjectiveCam...

FILE: shap_e/rendering/mc.py
  function marching_cubes (line 11) | def marching_cubes(
  function _create_flat_edge_indices (line 124) | def _create_flat_edge_indices(
  class McLookupTable (line 206) | class McLookupTable:
  function _lookup_table (line 229) | def _lookup_table(device: torch.device) -> McLookupTable:

FILE: shap_e/rendering/mesh.py
  class TriMesh (line 11) | class TriMesh:
    method load (line 30) | def load(cls, f: Union[str, BinaryIO]) -> "TriMesh":
    method save (line 58) | def save(self, f: Union[str, BinaryIO]):
    method has_vertex_colors (line 75) | def has_vertex_colors(self) -> bool:
    method write_ply (line 78) | def write_ply(self, raw_f: BinaryIO):
    method write_obj (line 90) | def write_obj(self, raw_f: BinaryIO):

FILE: shap_e/rendering/ply_util.py
  function write_ply (line 9) | def write_ply(

FILE: shap_e/rendering/point_cloud.py
  function preprocess (line 16) | def preprocess(data, channel):
  class PointCloud (line 23) | class PointCloud:
    method from_rgbd (line 36) | def from_rgbd(cls, vd: ViewData, num_views: Optional[int] = None) -> "...
    method load (line 95) | def load(cls, f: Union[str, BinaryIO]) -> "PointCloud":
    method save (line 110) | def save(self, f: Union[str, BinaryIO]):
    method write_ply (line 120) | def write_ply(self, raw_f: BinaryIO):
    method random_sample (line 131) | def random_sample(self, num_points: int, **subsample_kwargs) -> "Point...
    method farthest_point_sample (line 145) | def farthest_point_sample(
    method subsample (line 189) | def subsample(self, indices: np.ndarray, average_neighbors: bool = Fal...
    method select_channels (line 213) | def select_channels(self, channel_names: List[str]) -> np.ndarray:
    method nearest_points (line 217) | def nearest_points(self, points: np.ndarray, batch_size: int = 16384) ...
    method combine (line 236) | def combine(self, other: "PointCloud") -> "PointCloud":

FILE: shap_e/rendering/pytorch3d_util.py
  function render_images (line 33) | def render_images(
  function _deconstruct_tensor_props (line 114) | def _deconstruct_tensor_props(
  function convert_meshes (line 144) | def convert_meshes(raw_meshes: Sequence[TorchMesh], default_brightness=0...
  function convert_cameras (line 165) | def convert_cameras(
  function convert_cameras_torch (line 188) | def convert_cameras_torch(
  function blender_uniform_lights (line 207) | def blender_uniform_lights(
  class BidirectionalLights (line 233) | class BidirectionalLights(DirectionalLights):
    method diffuse (line 239) | def diffuse(self, normals, points=None) -> torch.Tensor:
    method specular (line 244) | def specular(self, normals, points, camera_position, shininess) -> tor...

FILE: shap_e/rendering/raycast/_utils.py
  function normalize (line 4) | def normalize(v: torch.Tensor) -> torch.Tensor:
  function cross_product (line 8) | def cross_product(v1: torch.Tensor, v2: torch.Tensor) -> torch.Tensor:

FILE: shap_e/rendering/raycast/cast.py
  function cast_camera (line 12) | def cast_camera(
  function cast_rays (line 30) | def cast_rays(rays: Rays, mesh: TriMesh, checkpoint: bool = False) -> Ra...
  class RayCollisionFunction (line 96) | class RayCollisionFunction(torch.autograd.Function):
    method forward (line 98) | def forward(
    method backward (line 111) | def backward(

FILE: shap_e/rendering/raycast/render.py
  function render_diffuse_mesh (line 16) | def render_diffuse_mesh(

FILE: shap_e/rendering/raycast/types.py
  class Rays (line 13) | class Rays:
    method normalized_directions (line 21) | def normalized_directions(self) -> torch.Tensor:
  class RayCollisions (line 26) | class RayCollisions:
    method collect (line 38) | def collect(cls, it: Iterable["RayCollisions"]) -> "RayCollisions":
  class TriMesh (line 57) | class TriMesh:
    method normals (line 63) | def normals(self) -> torch.Tensor:
    method from_numpy (line 74) | def from_numpy(cls, x: shap_e.rendering.mesh.TriMesh) -> "TriMesh":
    method to (line 86) | def to(self, *args, **kwargs) -> "TriMesh":

FILE: shap_e/rendering/torch_mesh.py
  class TorchMesh (line 10) | class TorchMesh:
    method tri_mesh (line 25) | def tri_mesh(self) -> TriMesh:

FILE: shap_e/rendering/view_data.py
  class Camera (line 9) | class Camera(ABC):
    method image_coords (line 15) | def image_coords(self) -> np.ndarray:
    method camera_rays (line 21) | def camera_rays(self, coords: np.ndarray) -> np.ndarray:
    method depth_directions (line 31) | def depth_directions(self, coords: np.ndarray) -> np.ndarray:
    method center_crop (line 46) | def center_crop(self) -> "Camera":
    method resize_image (line 53) | def resize_image(self, width: int, height: int) -> "Camera":
    method scale_scene (line 60) | def scale_scene(self, factor: float) -> "Camera":
  class ProjectiveCamera (line 68) | class ProjectiveCamera(Camera):
    method image_coords (line 86) | def image_coords(self) -> np.ndarray:
    method camera_rays (line 91) | def camera_rays(self, coords: np.ndarray) -> np.ndarray:
    method depth_directions (line 98) | def depth_directions(self, coords: np.ndarray) -> np.ndarray:
    method resize_image (line 101) | def resize_image(self, width: int, height: int) -> "ProjectiveCamera":
    method center_crop (line 117) | def center_crop(self) -> "ProjectiveCamera":
    method scale_scene (line 134) | def scale_scene(self, factor: float) -> "ProjectiveCamera":
  class ViewData (line 151) | class ViewData(ABC):
    method num_views (line 161) | def num_views(self) -> int:
    method channel_names (line 168) | def channel_names(self) -> List[str]:
    method load_view (line 177) | def load_view(self, index: int, channels: List[str]) -> Tuple[Camera, ...
  class MemoryViewData (line 186) | class MemoryViewData(ViewData):
    method __init__ (line 191) | def __init__(self, channels: Dict[str, np.ndarray], cameras: List[Came...
    method num_views (line 197) | def num_views(self) -> int:
    method channel_names (line 201) | def channel_names(self) -> List[str]:
    method load_view (line 204) | def load_view(self, index: int, channels: List[str]) -> Tuple[Camera, ...

FILE: shap_e/util/collections.py
  class AttrDict (line 8) | class AttrDict(OrderedDict[K, V], Generic[K, V]):
    method __init__ (line 18) | def __init__(self, *args, **kwargs):
    method __contains__ (line 28) | def __contains__(self, key):
    method __setitem__ (line 35) | def __setitem__(self, key, value):
    method __getitem__ (line 50) | def __getitem__(self, key):
    method all_keys (line 61) | def all_keys(
    method dumpable (line 75) | def dumpable(self, strip=True):
    method map (line 91) | def map(
    method __eq__ (line 113) | def __eq__(self, other):
    method combine (line 116) | def combine(

FILE: shap_e/util/data_util.py
  function load_or_create_multimodal_batch (line 19) | def load_or_create_multimodal_batch(
  function load_or_create_pc (line 85) | def load_or_create_pc(
  function load_or_create_multiview (line 129) | def load_or_create_multiview(
  function mv_to_pc (line 195) | def mv_to_pc(multiview: ViewData, random_sample_count: int, point_count:...
  function normalize_input_batch (line 215) | def normalize_input_batch(batch: AttrDict, *, pc_scale: float, color_sca...
  function process_depth (line 229) | def process_depth(depth_img: np.ndarray, image_size: int) -> np.ndarray:
  function process_image (line 235) | def process_image(

FILE: shap_e/util/image_util.py
  function center_crop (line 11) | def center_crop(
  function resize (line 31) | def resize(
  function get_alpha (line 78) | def get_alpha(img: Image.Image) -> Image.Image:
  function remove_alpha (line 91) | def remove_alpha(img: Image.Image, mode: str = "random") -> Image.Image:
  function _black_bg (line 119) | def _black_bg(h: int, w: int) -> np.ndarray:
  function _gray_bg (line 123) | def _gray_bg(h: int, w: int) -> np.ndarray:
  function _checker_bg (line 127) | def _checker_bg(h: int, w: int) -> np.ndarray:
  function _noise_bg (line 139) | def _noise_bg(h: int, w: int) -> np.ndarray:
  function load_image (line 143) | def load_image(image_path: str) -> Image.Image:
  function make_tile (line 150) | def make_tile(images: List[Union[np.ndarray, Image.Image]], columns=8) -...
  function round_up (line 169) | def round_up(n: int, b: int) -> int:

FILE: shap_e/util/io.py
  function read_config (line 11) | def read_config(path_or_file: Union[str, io.IOBase]) -> Any:
  function buffered_writer (line 28) | def buffered_writer(raw_f: BinaryIO) -> Iterator[io.BufferedIOBase]:

FILE: shap_e/util/notebooks.py
  function create_pan_cameras (line 16) | def create_pan_cameras(size: int, device: torch.device) -> Differentiabl...
  function decode_latent_images (line 47) | def decode_latent_images(
  function decode_latent_mesh (line 65) | def decode_latent_mesh(
  function gif_widget (line 79) | def gif_widget(images):