SYMBOL INDEX (82 symbols across 8 files)

FILE: engine.py
  function train_one_epoch (line 29) | def train_one_epoch(model: torch.nn.Module,

FILE: main.py
  function get_args_parser (line 26) | def get_args_parser():
  function main (line 102) | def main(args):

FILE: models.py
  function modulate (line 12) | def modulate(x, shift, scale):
  class TimestepEmbedder (line 15) | class TimestepEmbedder(nn.Module):
    method __init__ (line 19) | def __init__(self, hidden_size, frequency_embedding_size=256):
    method timestep_embedding (line 29) | def timestep_embedding(t, dim, max_period=10000):
    method forward (line 49) | def forward(self, t):
  class MPFourier (line 54) | class MPFourier(torch.nn.Module):
    method __init__ (line 55) | def __init__(self, num_channels, bandwidth=1):
    method forward (line 60) | def forward(self, x):
  function normalize (line 69) | def normalize(x, dim=None, eps=1e-4):
  function mp_silu (line 76) | def mp_silu(x):
  function mp_sum (line 79) | def mp_sum(a, b, t=0.5):
  class MPConv (line 83) | class MPConv(torch.nn.Module):
    method __init__ (line 84) | def __init__(self, in_channels, out_channels, kernel):
    method forward (line 89) | def forward(self, x, gain=1):
  class PointEmbed (line 102) | class PointEmbed(nn.Module):
    method __init__ (line 103) | def __init__(self, hidden_dim=48, dim=128, other_dim=0):
    method embed (line 124) | def embed(input, basis):
    method forward (line 130) | def forward(self, input):
  class Network (line 144) | class Network(nn.Module):
    method __init__ (line 145) | def __init__(
    method forward (line 182) | def forward(self, x, t):
  class EDMPrecond (line 208) | class EDMPrecond(torch.nn.Module):
    method __init__ (line 209) | def __init__(self,
    method forward (line 226) | def forward(self, x, sigma, force_fp32=False, **model_kwargs):
    method round_sigma (line 243) | def round_sigma(self, sigma):
    method sample (line 247) | def sample(self, cond=None, batch_seeds=None, channels=3, num_steps=18):
    method inverse (line 261) | def inverse(self, cond=None, samples=None, channels=3, num_steps=18):
  class StackedRandomGenerator (line 265) | class StackedRandomGenerator:
    method __init__ (line 266) | def __init__(self, device, seeds):
    method randn (line 270) | def randn(self, size, **kwargs):
    method randn_like (line 274) | def randn_like(self, input):
    method randint (line 277) | def randint(self, *args, size, **kwargs):
  function edm_sampler (line 281) | def edm_sampler(
  function inverse_edm_sampler (line 327) | def inverse_edm_sampler(
  class EDMLoss (line 383) | class EDMLoss:
    method __init__ (line 384) | def __init__(self, P_mean=-1.2, P_std=1.2, sigma_data=1, dist='Gaussia...
    method __call__ (line 391) | def __call__(self, net, inputs, labels=None, augment_pipe=None, init_n...

FILE: normalize.py
  function normalize_meshes (line 19) | def normalize_meshes(mesh):

FILE: points.py
  class Points (line 9) | class Points(data.Dataset):
    method __init__ (line 10) | def __init__(self, ply_path):
    method __len__ (line 21) | def __len__(self):
    method __getitem__ (line 24) | def __getitem__(self, idx):

FILE: util/lr_decay.py
  function param_groups_lrd (line 11) | def param_groups_lrd(model, weight_decay=0.05, no_weight_decay_list=[], ...
  function get_layer_id_for_vit (line 60) | def get_layer_id_for_vit(name, num_layers):

FILE: util/lr_sched.py
  function adjust_learning_rate (line 9) | def adjust_learning_rate(optimizer, epoch, args):

FILE: util/misc.py
  class SmoothedValue (line 24) | class SmoothedValue(object):
    method __init__ (line 29) | def __init__(self, window_size=20, fmt=None):
    method update (line 37) | def update(self, value, n=1):
    method synchronize_between_processes (line 42) | def synchronize_between_processes(self):
    method median (line 56) | def median(self):
    method avg (line 61) | def avg(self):
    method global_avg (line 66) | def global_avg(self):
    method max (line 70) | def max(self):
    method value (line 74) | def value(self):
    method __str__ (line 77) | def __str__(self):
  class MetricLogger (line 86) | class MetricLogger(object):
    method __init__ (line 87) | def __init__(self, delimiter="\t"):
    method update (line 91) | def update(self, **kwargs):
    method __getattr__ (line 100) | def __getattr__(self, attr):
    method __str__ (line 108) | def __str__(self):
    method synchronize_between_processes (line 116) | def synchronize_between_processes(self):
    method add_meter (line 120) | def add_meter(self, name, meter):
    method log_every (line 123) | def log_every(self, iterable, print_freq, header=None):
  function setup_for_distributed (line 170) | def setup_for_distributed(is_master):
  function is_dist_avail_and_initialized (line 187) | def is_dist_avail_and_initialized():
  function get_world_size (line 195) | def get_world_size():
  function get_rank (line 201) | def get_rank():
  function is_main_process (line 207) | def is_main_process():
  function save_on_master (line 211) | def save_on_master(*args, **kwargs):
  function init_distributed_mode (line 216) | def init_distributed_mode(args):
  class NativeScalerWithGradNormCount (line 251) | class NativeScalerWithGradNormCount:
    method __init__ (line 254) | def __init__(self):
    method __call__ (line 257) | def __call__(self, loss, optimizer, clip_grad=None, parameters=None, c...
    method state_dict (line 273) | def state_dict(self):
    method load_state_dict (line 276) | def load_state_dict(self, state_dict):
  function get_grad_norm_ (line 280) | def get_grad_norm_(parameters, norm_type: float = 2.0) -> torch.Tensor:
  function save_model (line 295) | def save_model(args, epoch, model, model_without_ddp, optimizer, loss_sc...
  function load_model (line 315) | def load_model(args, model_without_ddp, optimizer, loss_scaler):
  function all_reduce_mean (line 332) | def all_reduce_mean(x):