(self, index)

(self, idx)

(self, index)

(self, index)

(self, index)

(self, index)

(self, i)

(self, model)

( self, checkpoint_prefix='checkpoint', recovery_prefix='recovery',

(self)

(self, fmt='%(levelname)s: %(message)s')

(self, optimizer: torch.optim.Optimizer, t_initial: int, lb

(self, optimizer, decay_rate=0.1, patience_t=10,

(self, optimizer: torch.optim.Optimizer, param_group_field: str,

(self, optimizer: torch.optim.Optimizer, t_initial: int, t_

(self, optimizer: torch.optim.Optimizer, decay_t: float, de

(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8, weight_decay=0)

(self, base_optimizer, alpha=0.5, k=6)

(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8, weight_decay=1e-2, amsgrad=False)

(self, params, lr=1e-2, alpha=0.9, eps=1e-10, weight_decay=0, momentum=0., centered=False, de

(self, params, lr=2e-3, betas=(0.9, 0.999), eps=1e-8, weight_decay=0, schedule_decay=4e-3)

(self, params, lr=1e-3, betas=(0.95, 0.98), eps=1e-8, weight_decay=0, grad_averaging=False, a

(self, params, grad_averaging=False, lr=0.1, betas=(0.95, 0.98), eps=1e-8, weight_decay=0)

(self, loader, mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEF

(self, loader, mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEF

(self, loader, mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEF

(self, name, prob=0.5, magnitude=10, hparams=None)

(self, policy)

(self, ops, num_layers=2, choice_weights=None)

(self, ops, alpha=1., width=3, depth=-1, blended=False)

(self, dtype=torch.float32)

(self, size, scale=(0.08, 1.0), ratio=(3. / 4., 4. / 3.), interpolation='bilinear')

(self, scale=(0.9, 1.1), interpolation='bilinear')

(self, p=0.5)

(self, p, blur_radiu)

(self, rotate_range)

(self, probability)

(self, is_training=False, size=224, interpolation='bicubic')

( self, root, result_file, load_bytes=False, trans

(self, datasets)

( self, roots, class_names, load_bytes=False, tran

( self, roots, class_names, load_bytes=False, tran

( self, root, result_file, load_bytes=False, trans

(self, root, load_bytes=False, transform=None, class_map='')

(self, dataset, num_splits=2)

(self, dataset, num_replicas=None, rank=None)

(self, mixup_alpha=1., label_smoothing=0.1, num_classes=1000)

( self, probability=0.5, min_area=0.02, max_area=1 / 3, min_aspect=0.3, max_aspect=Non

(self, inplanes, planes, stride=1, dilation=1, **_)

(self, inplanes, outplanes, stride=1, dilation=1, cardinality=1, base_width=64)

(self, inplanes, outplanes, stride=1, dilation=1, scale=4, cardinality=8, base_width=4)

(self, in_channels, out_channels, kernel_size, residual)

(self, levels, block, in_channels, out_channels, stride=1, dilation=1, cardinality=1, base_wi

(self, in_channels, out_channels, kernel_size=1, stride=1, padding=0, dilation=1, bias=False)

(self, kernel_size, stride=1, padding=1, zero_pad=False)

(self, in_channels, out_channels, dw_kernel_size, dw_stride, dw_padding)

(self, in_channels, out_channels, kernel_size, stride=1, stem_cell=False, zero_pad=False)

(self, in_channels, out_channels, kernel_size, stride=1)

(self, in_channels, out_channels)

(self, in_channels_left, out_channels_left, in_channels_right, out_channels_right)

(self, num_classes=1001, in_chans=3, drop_rate=0.5, global_pool='avg')

(self, inplanes, planes, kernel_size=3, stride=1, dilation=1, bias=False, norm_layer=None, no

(self, num_classes=1000, in_chans=3, output_stride=32, norm_layer=nn.BatchNorm2d, norm_kwargs

(self, num_classes=1000, in_chans=3, output_stride=32, norm_layer=nn.BatchNorm2d, norm_kwargs

(self, inplanes, planes, stride=1, downsample=None, cardinality=1, base_width=26, scale=4, di

(self, channels, reduction)

(self, inplanes, planes, groups, reduction, stride=1, downsample=None)

(self, inplanes, planes, groups, reduction, stride=1, downsample=None)

(self, inplanes, planes, groups, reduction, stride=1, downsample=None, base_width=4)

(self, inplanes, planes, groups, reduction, stride=1, downsample=None)

(self, num_branches, blocks, num_blocks, num_inchannels, num_channels, fuse_method, multi_sca

(self, in_chs, activation_fn=nn.ReLU(inplace=True))

(self, in_chs, out_chs, kernel_size, stride, padding=0, groups=1, activation_fn=nn.ReLU(inpla

(self, num_init_features, kernel_size=7, in_chans=3, padding=3, activation_fn=nn.ReLU(inplace

( self, in_chs, num_1x1_a, num_3x3_b, num_1x1_c, inc, groups, block_type='normal', b=False)

(self, num_input_features, growth_rate, bn_size, drop_rate)

(self, num_layers, num_input_features, bn_size, growth_rate, drop_rate)

(self, num_input_features, num_output_features)

(self, block_args, out_indices=(0, 1, 2, 3, 4), feature_location='pre_pwl', in_chans=3, stem_

(self, in_planes, out_planes, kernel_size, stride, padding=0)

(self)

(self)

(self)

(self)

(self)

(self)

(self)

(self, num_classes=1001, in_chans=3, drop_rate=0., global_pool='avg')

(self, in_chs, skip_chs, mid_chs, out_chs, is_first, stride, dilation=1)

(self)

(self, stride=2, padding=1)

(self, in_channels, out_channels, dw_kernel, dw_stride, dw_padding, bias=False)

(self, in_channels, out_channels, kernel_size, stride, padding, bias=False)

(self, in_channels, out_channels, kernel_size, stride, padding, bias=False)

(self, in_channels, out_channels, kernel_size, stride, padding, z_padding=1, bias=False)

(self, stem_size, num_channels)

(self, in_channels_left, out_channels_left, in_channels_right, out_channels_right)

(self, in_channels_left, out_channels_left, in_channels_right, out_channels_right)

(self, in_channels_left, out_channels_left, in_channels_right, out_channels_right)