Method__init__(
self,
dep_mul,
wid_mul,
out_features=("dark3", "dark4", "dark5"),
de
detector/yolox/yolox/models/darknet.py:98
Method__init__(
self, in_channels, out_channels, ksize, stride, groups=1, bias=False, act="silu"
)
detector/yolox/yolox/models/network_blocks.py:32
Method__init__(self, in_channels, out_channels, ksize, stride=1, act="silu")
detector/yolox/yolox/models/network_blocks.py:60
Method__init__(
self,
in_channels,
out_channels,
shortcut=True,
expansion=0.5,
detector/yolox/yolox/models/network_blocks.py:81
Method__init__(
self, in_channels, out_channels, kernel_sizes=(5, 9, 13), activation="silu"
)
detector/yolox/yolox/models/network_blocks.py:125
Method__init__(
self,
depth=1.0,
width=1.0,
in_features=("dark3", "dark4", "dark5"),
detector/yolox/yolox/models/yolo_pafpn.py:17
Method__init__(self, in_channels, out_channels, kernel_size, stride=1, dilation=1, padding='', bias=False,
detector/efficientdet/effdet/efficientdet.py:44
Method__init__(self, in_channels, out_channels, kernel_size=3, stride=1, dilation=1, padding='', bias=False,
detector/efficientdet/effdet/efficientdet.py:65
Method__init__(self, in_channels, out_channels, reduction_ratio=1., pad_type='', pooling_type='max',
norm_l
detector/efficientdet/effdet/efficientdet.py:93
Method__init__(self, feature_info, fpn_config, fpn_channels, inputs_offsets, target_reduction, pad_type='',
detector/efficientdet/effdet/efficientdet.py:143
Method__init__(self, feature_info, fpn_config, fpn_channels, num_levels=5, pad_type='',
pooling_type='max',
detector/efficientdet/effdet/efficientdet.py:196
Method__init__(self, config, num_outputs, norm_layer=nn.BatchNorm2d, norm_kwargs=None,
act_layer=_ACT_LAYER
detector/efficientdet/effdet/efficientdet.py:347
Method__init__(self, cfg, opt, save_video=False,
video_save_opt=DEFAULT_VIDEO_SAVE_OPT,
qu
alphapose/utils/writer_smpl.py:24
Method__init__(self, cfg, opt, save_video=False,
video_save_opt=DEFAULT_VIDEO_SAVE_OPT,
qu
alphapose/utils/writer.py:25
Method__init__(self, input_source, detector, cfg, opt, mode='image', batchSize=1, queueSize=128)
alphapose/utils/detector.py:16
Method__init__(self, dataset, scale_factor, add_dpg,
input_size, output_size, rot, sigma,
alphapose/utils/presets/simple_transform.py:53
Method__init__(self, dataset, scale_factor, color_factor, occlusion, add_dpg,
input_size, output_size, dept
alphapose/utils/presets/simple_transform_3d_smpl.py:81
Method__init__(self, in_channels, out_channels, norm_layer, kernel=1, stride=1, dropout=0.1, bias=False)
alphapose/models/hardnet.py:45
Method__init__(self, in_channels, out_channels, norm_layer, kernel=3, stride=1, padding=0, bias=False)
alphapose/models/hardnet.py:73
Method__init__(self, in_channels, growth_rate, grmul, n_layers, norm_layer, keepBase=False, residual_out=False, dwconv=False
alphapose/models/hardnet.py:122
Method__init__(self, in_channels, growth_rate, grmul, n_layers, norm_layer, dwconv=False)
alphapose/models/hardnet.py:195
Method__init__(self, num_branches, blocks, num_blocks, num_inchannels,
num_channels, fuse_method, multi_sca
alphapose/models/hrnet.py:99
Method__init__(self, inplanes, planes, stride=1,
downsample=None, reduction=False,
norm_la
alphapose/models/layers/ShuffleResnet.py:63
Method__init__(self, architecture, norm_layer=nn.BatchNorm2d, dcn=None, stage_with_dcn=(False, False, False, False))
alphapose/models/layers/ShuffleResnet.py:129
Method__init__(self, inplanes, planes, stride=1, downsample=None,
reduction=False, norm_layer=nn.BatchNorm2
alphapose/models/layers/SE_Resnet.py:21
Method__init__(self, inplanes, planes, stride=1,
downsample=None, reduction=False,
norm_la
alphapose/models/layers/SE_Resnet.py:62
Method__init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
base_width=64, dilation=1, norm
alphapose/models/layers/Resnet.py:20
Method__init__(self, inplanes, planes, stride=1,
downsample=None, norm_layer=nn.BatchNorm2d, dcn=None)
alphapose/models/layers/Resnet.py:60
Method__init__(self, inplanes, planes, dcn,
kernel_size, stride=1,
padding=0, bias=False)
alphapose/models/layers/dcn/DCN.py:17