Functions — github.com/Wuziyi616/LEOD

CodeHub MCPcopy Create free account

hub / github.com/Wuziyi616/LEOD / functions

Functions938 in github.com/Wuziyi616/LEOD

⨍ Functions 938◇ Types & classes 194↳ Endpoints 1

(self, model_cfg: DictConfig, ssod: bool = False)

models/detection/yolox_extension/models/detector.py:21

( self, depth: float = 1.0, in_stages: Tuple[int, ...] = (2, 3, 4),

models/detection/yolox_extension/models/yolo_pafpn.py:23

(self, dim: int, skip_first_norm: bool, attention_cfg: Dict

models/detection/recurrent_backbone/maxvit_rnn.py:121

(self, dim_in: int, stage_dim: int, spatial_downsample_fact

models/detection/recurrent_backbone/maxvit_rnn.py:146

( self, in_channels, out_channels, ksize, stride, groups=1, bias=False, act="silu" )

models/detection/yolox/models/network_blocks.py:32

( self, in_channels, out_channels, shortcut=True, expansion=0.5,

models/detection/yolox/models/network_blocks.py:81

Args: in_channels (int): input channels. out_channels (int): output channels. n (int): number of Bottlene

models/detection/yolox/models/network_blocks.py:107

( self, num_classes=80, strides=(8, 16, 32), in_channels=(256,

models/detection/yolox/models/yolo_head.py:24

(self, alpha=0.25, gamma=2, reduction='none')

models/detection/yolox/models/losses.py:72

(self, dim: int, dws_conv: bool = True, # RVT uses False d

models/layers/rnn.py:11

(self, dim: int, init_values: float=1e-5, inplace: bool=False)

models/layers/maxvit/maxvit.py:46

(self, dim: int, channel_last: bool, expansion_ratio: int,

models/layers/maxvit/maxvit.py:86

models/layers/maxvit/maxvit.py:122

(self, dim_in: int, dim_out: int, downsample_factor: int,

models/layers/maxvit/maxvit.py:147

( self, dim: int, partition_type: PartitionType, attention_cfg

models/layers/maxvit/maxvit.py:193

( self, dim: int, dim_head: int = 32, bias: bool = True)

models/layers/maxvit/maxvit.py:309

( self, dim: int, dim_head: int = 32, bias: bool = True)

models/layers/maxvit/maxvit.py:330

( self, drop_prob: float = 0.1, block_size: int = 7, gamma_sca

models/layers/maxvit/layers/drop.py:108

(self, mode: bool)

models/layers/maxvit/layers/config.py:30

(self, mode: bool)

models/layers/maxvit/layers/config.py:49

(self, mode: bool)

models/layers/maxvit/layers/config.py:68

( self, scriptable: Optional[bool] = None, exportable: Optional[bool] = No

models/layers/maxvit/layers/config.py:86

(self, in_channels, block_size, groups, act_layer=nn.ReLU, norm_layer=nn.BatchNorm2d)

models/layers/maxvit/layers/non_local_attn.py:74

( self, in_channels, block_size=7, groups=2, rd_ratio=0.25, rd_channels=None, rd_divisor=8,

models/layers/maxvit/layers/non_local_attn.py:129

( self, in_channel, out_channels, kernel_size, stride=1, padding='SAME', dilation=1, g

models/layers/maxvit/layers/std_conv.py:56

( self, in_channels, out_channels, kernel_size, stride=1, padding=None, dilation=1, gr

models/layers/maxvit/layers/std_conv.py:85

( self, in_channels, out_channels, kernel_size, stride=1, padding='SAME', dilation=1,

models/layers/maxvit/layers/std_conv.py:114

( self, dim, dim_out=None, feat_size=None, stride=1, num_heads=4, dim_head=None, qk_ra

models/layers/maxvit/layers/bottleneck_attn.py:106

( self, in_features: int, out_features: int = None, embed_dim:

models/layers/maxvit/layers/attention_pool2d.py:30

(self, kernel_size: int, stride=None, padding=0, dilation=1, ceil_mode=False)

models/layers/maxvit/layers/pool2d_same.py:45

(self, inplace: bool = False)

models/layers/maxvit/layers/activations_jit.py:33

(self, inplace: bool = False)

models/layers/maxvit/layers/activations_jit.py:55

(self, inplace: bool = False)

models/layers/maxvit/layers/activations_jit.py:69

(self, inplace: bool = False)

models/layers/maxvit/layers/activations_jit.py:86

(self, num_features, eps=1e-5, momentum=0.1, affine=True, apply_act=True, act_layer="leaky_re

models/layers/maxvit/layers/inplace_abn.py:40

(self, in_chs, num_classes, pool_type='avg', drop_rate=0., use_conv=False)

models/layers/maxvit/layers/classifier.py:41

(self, channels, add_maxpool=False, gate_layer='hard_sigmoid', **_)

models/layers/maxvit/layers/squeeze_excite.py:59

(self, inplace: bool = False)

models/layers/maxvit/layers/activations_me.py:53

(self, inplace: bool = False)

models/layers/maxvit/layers/activations_me.py:127

(self, inplace: bool = False)

models/layers/maxvit/layers/activations_me.py:171

(self, inplace: bool = False)

models/layers/maxvit/layers/activations_me.py:211

(self, d_model, nhead=8, dim_feedforward=2048, dropout=0.1, activation="relu", layer_norm_eps

models/layers/maxvit/layers/ml_decoder.py:36

(self, num_classes, num_of_groups=-1, decoder_embedding=768, initial_num_features=2048)

models/layers/maxvit/layers/ml_decoder.py:104

(self, channels, use_attn=True, fuse_add=False, fuse_scale=True, init_last_zero=False, rd_rat

models/layers/maxvit/layers/global_context.py:21

(self, in_channels, out_channels, kernel_size=3, stride=1, dilation=1, padding='', bias=False,

models/layers/maxvit/layers/separable_conv.py:17

(self, in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bia

models/layers/maxvit/layers/conv2d_same.py:24

( self, channels, feat_size=None, extra_params=False, extent=0, use_mlp=True, rd_ratio

models/layers/maxvit/layers/gather_excite.py:28

( self, dim, dim_out=None, feat_size=None, stride=1, num_heads=4, dim_head=16, r=9, qk

models/layers/maxvit/layers/lambda_layer.py:67

( self, channels, rd_ratio=1./16, rd_channels=None, rd_divisor=1, act_layer=nn.ReLU, g

models/layers/maxvit/layers/cbam.py:22

( self, channels, rd_ratio=1./16, rd_channels=None, rd_divisor=1, act_layer=nn.ReLU, g

models/layers/maxvit/layers/cbam.py:42

(self, kernel_size=7, gate_layer='sigmoid')

models/layers/maxvit/layers/cbam.py:57

(self, kernel_size=7, gate_layer='sigmoid')

models/layers/maxvit/layers/cbam.py:71

( self, channels, rd_ratio=1./16, rd_channels=None, rd_divisor=1, spatial_kernel_size=

models/layers/maxvit/layers/cbam.py:99

(self, num_features, apply_act=True, momentum=0.1, eps=1e-5, **_)

models/layers/maxvit/layers/evo_norm.py:139

(self, num_features, apply_act=True, momentum=0.1, eps=1e-5, **_)

models/layers/maxvit/layers/evo_norm.py:174

(self, num_features, groups=32, group_size=None, apply_act=True, eps=1e-5, **_)

models/layers/maxvit/layers/evo_norm.py:209

(self, num_features, groups=32, group_size=None, apply_act=True, eps=1e-3, **_)

models/layers/maxvit/layers/evo_norm.py:240

( self, num_features, groups=32, group_size=None, apply_act=True, act_layer=None, eps=

models/layers/maxvit/layers/evo_norm.py:257

( self, num_features, groups=32, group_size=None, apply_act=True, act_layer=None, eps=

models/layers/maxvit/layers/evo_norm.py:292

( self, num_features, groups=32, group_size=None, apply_act=True, act_layer=None, eps=

models/layers/maxvit/layers/evo_norm.py:307

( self, num_features, groups=32, group_size=None, apply_act=True, act_layer=None, eps=

models/layers/maxvit/layers/evo_norm.py:341

(self, num_channels, **kwargs)

models/layers/maxvit/layers/norm.py:33

(self, num_channels, eps=1e-6, affine=True)

models/layers/maxvit/layers/norm.py:47

(self, num_channels, eps=1e-6, affine=True)

models/layers/maxvit/layers/norm.py:61

(self, num_channels, eps=1e-6)

models/layers/maxvit/layers/norm.py:108

(self, inplace: bool = False)

models/layers/maxvit/layers/activations.py:21

(self, inplace: bool = False)

models/layers/maxvit/layers/activations.py:52

(self, inplace: bool = False)

models/layers/maxvit/layers/activations.py:66

(self, inplace: bool = False)

models/layers/maxvit/layers/activations.py:80

(self, inplace: bool = False)

models/layers/maxvit/layers/activations.py:96

(self, inplace: bool = False)

models/layers/maxvit/layers/activations.py:116

(self, num_parameters: int = 1, init: float = 0.25, inplace: bool = False)

models/layers/maxvit/layers/activations.py:127

(self, inplace: bool = False)

models/layers/maxvit/layers/activations.py:141

(self, in_features, hidden_features=None, out_features=None, act_layer=nn.Sigmoid, bias=True, drop=0.)

models/layers/maxvit/layers/mlp.py:39

( self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, gate_

models/layers/maxvit/layers/mlp.py:72

( self, in_features, hidden_features=None, out_features=None, act_layer=nn.ReLU, norm_

models/layers/maxvit/layers/mlp.py:106

(self, dim, max_res=224, linear_bands: bool = False)

models/layers/maxvit/layers/pos_embed.py:196

(self, channels=None, kernel_size=3, gamma=2, beta=1, act_layer=None, gate_layer='sigmoid')

models/layers/maxvit/layers/eca.py:121

(self, channels, filt_size=3, stride=2)

models/layers/maxvit/layers/blur_pool.py:29

( self, in_channels, out_channels, kernel_size=1, stride=1, padding='', dilation=1, groups=1,

models/layers/maxvit/layers/conv_bn_act.py:59

(self, flatten=False)

models/layers/maxvit/layers/adaptive_avgmax_pool.py:53

(self, output_size=1)

models/layers/maxvit/layers/adaptive_avgmax_pool.py:71

(self, output_size=1, pool_type='fast', flatten=False)

models/layers/maxvit/layers/adaptive_avgmax_pool.py:82

( self, num_features, eps=1e-5, momentum=0.1, affi

models/layers/maxvit/layers/norm_act.py:33

( self, normalization_shape: Union[int, List[int], torch.Size], eps=1e-5, affine=True,

models/layers/maxvit/layers/norm_act.py:206

( self, num_channels, eps=1e-5, affine=True, apply_act=True, act_layer=nn.ReLU, inplac

models/layers/maxvit/layers/norm_act.py:230

(self, radix, cardinality)

models/layers/maxvit/layers/split_attn.py:17

(self, kernel_size=3, stride=1, padding=0, same=False)

models/layers/maxvit/layers/median_pool.py:18

Args: block_size (int): block size win_size (int): neighbourhood window size dim_head (int): attention he

models/layers/maxvit/layers/halo_attn.py:67

(self, in_channels, out_channels, kernel_size=3, stride=1, padding='', dilation=1, groups=1,

models/layers/maxvit/layers/cond_conv2d.py:43

(self, num_features, apply_act=True, act_layer=nn.ReLU, inplace=None, rms=True, eps=1e-5, **_)

models/layers/maxvit/layers/filter_response_norm.py:46

(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768, norm_layer=None, flatten=True)

models/layers/maxvit/layers/patch_embed.py:18

(self, no_jit=False)

models/layers/maxvit/layers/space_to_depth.py:31

(self, block_size)

models/layers/maxvit/layers/space_to_depth.py:44

Selective Kernel Attention Module Selective Kernel attention mechanism factored out into its own module.

models/layers/maxvit/layers/selective_kernel.py:23

(self, in_channels, out_channels, kernel_size=3, stride=1, padding='', dilation=1, depthwise=

models/layers/maxvit/layers/mixed_conv2d.py:26

(self, base, original_pool=7)

models/layers/maxvit/layers/test_time_pool.py:17

(self, num_features, eps=1e-5, momentum=0.1, affine=True, track_running_stats=True, num_split

models/layers/maxvit/layers/split_batchnorm.py:20

data/utils/stream_concat_datapipe.py:21

data/utils/stream_concat_datapipe.py:105

← previous next →501–600 of 938, ranked by callers