(self, i: int)

(self, i: int)

(self, i)

(self, i)

(self, i)

(self, i)

(self, item)

(self, i)

(self)

(self, in_channels: int, hidden_channels: int)

(self, in_channels: int, hidden_channels: int)

(self, name, fmt=':f')

(self, num_batches, meters, prefix="")

(self, path, l=2, ctfm=None, stfm=None)

(self)

(self, root: str, classes: List[str], capacity: int = 200)

(self, params, lr=1e-3, eps=1e-8, weight_decay=0)

(self, params, lr=1e-3, beta=0.9, weight_decay=0)

(self, params, lr=1e-3, betas=(0.9, 0.999),

(self, params, lr=1e-3, betas=(0.9, 0.999),

(self, base_optimizer, alpha=0.5, k=5)

(self, m: nn.Module)

(self, m)

(self, except_names: List[str] = [])

(self, shape: Tuple[int, ...], sd: float = 0.01, decay_powe

(self)

(self, *shape: int, init_sd: float = 0.06, init_img: torch.

(self, optimizer, schedule: List[Tuple[float, float, float]],

(self, optimizer, total_iters: int, warmup_ratio: float = 0

(self, optimizer, total_iters: int, warmup_ratio: float = 0

(self, opt, lr: Tuple[float, float], num_iters: int,

(self, optimizer: Optimizer, n_iters_total: int, tanh_lower

(self, low: float, high: float)

(self, low, high)

(self, choices)

(self, **hyperparams)

(self, x, y)

(self, params)

(self, **hyperparams)

(self, loc: torch.Tensor, scale: torch.Tensor)

(self, weights, locs, scales, dim)

(self, weights: torch.Tensor, locs: torch.Tensor, scales: torch.Tensor)

(self, topk: int, labels: List[str], center_value: float =

(self, topk, labels, center_value=0)

(self)

(self, beta: float = 0.6)

(self, name, post_each_batch=True, k=100)

(self, name, beta: float = 0.9, post_each_batch: bool = True)

(self, name, post_each_batch=True)

(self, k: int = 5, post_each_batch: bool = True, avg_type:

(self, post_each_batch=True, avg_type='window')

(self, post_each_batch=True, epoch_ends=True)

(self, opt, accumulation=1, clip_grad_norm=None,

(self, sched, metric='loss', step_each_batch=False)

(self, visdom_env='main', log_every=10, prefix='',

(self, log_dir=MISSING, log_every=10, prefix='',

(self, log_every=10, prefix='')

(self, filename_base, objects, max_saves=10, key_best=None)

(self, original: nn.Module, copy: nn.Module, beta: float =

(self)

(self, nb_show, classes, post_each_batch=True)

(self, nb_show, classes, post_each_batch=True)

(self, labels, normalize=False)

(self, loop)

(self, loop, run_every=100, prefix='test', init_fun=None)

(self)

( self, real_key: str = 'batch.0', fake_key: str = 'fake', dev

(self, real_key: str, fake_key: str, model: str = 'alex')

(self, n_scales=3)

(self, gamma)

(self, model, layer, input_size, *,

(self, gamma)

(self, n_scales=3)

(self, gamma)

(self, device="cpu", visdom_env='style')

(self)

(self, target_loss: float, growth: float = 0.01)

(self, every=4)

(self, gamma)

(self, gamma)

(self, G: nn.Module, D: nn.Module)

(self, G: nn.Module, D: nn.Module, l1_gain: float)

(self, model, dream_layer)

(self)

(self)

(self, call_fun, loader)

(self, data)

(self, stride: int)

(self, B: int, init: Optional[torch.Tensor] = None)

(self, size, mode=Image.BILINEAR)

(self, padding_mode='reflect', fill=0)

(self, sz, padding_mode='constant', fill=0)

(self, transforms)

(self, size, scale=1, ratio=1, interpolati

(self, std)

(self, min_bits: int = 4, max_bits: int = 8)

(self, max_thresh: int = 128)

(self, min_size: float, max_size: float)

(self, min_ratio: float, max_ratio: float, patch_size: Opti

( self, min_ratio: int = 1, max_ratio: int = 3, p: float = 0.5