MCPcopy Create free account
hub / github.com/NVIDIA/semantic-segmentation / HighResolutionModule

Class HighResolutionModule

network/hrnetv2.py:109–254  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

107
108
109class HighResolutionModule(nn.Module):
110 def __init__(self, num_branches, blocks, num_blocks, num_inchannels,
111 num_channels, fuse_method, multi_scale_output=True):
112 super(HighResolutionModule, self).__init__()
113 self._check_branches(
114 num_branches, blocks, num_blocks, num_inchannels, num_channels)
115
116 self.num_inchannels = num_inchannels
117 self.fuse_method = fuse_method
118 self.num_branches = num_branches
119
120 self.multi_scale_output = multi_scale_output
121
122 self.branches = self._make_branches(
123 num_branches, blocks, num_blocks, num_channels)
124 self.fuse_layers = self._make_fuse_layers()
125 self.relu = nn.ReLU(inplace=relu_inplace)
126
127 def _check_branches(self, num_branches, blocks, num_blocks,
128 num_inchannels, num_channels):
129 if num_branches != len(num_blocks):
130 error_msg = 'NUM_BRANCHES({}) <> NUM_BLOCKS({})'.format(
131 num_branches, len(num_blocks))
132 logx.msg(error_msg)
133 raise ValueError(error_msg)
134
135 if num_branches != len(num_channels):
136 error_msg = 'NUM_BRANCHES({}) <> NUM_CHANNELS({})'.format(
137 num_branches, len(num_channels))
138 logx.msg(error_msg)
139 raise ValueError(error_msg)
140
141 if num_branches != len(num_inchannels):
142 error_msg = 'NUM_BRANCHES({}) <> NUM_INCHANNELS({})'.format(
143 num_branches, len(num_inchannels))
144 logx.msg(error_msg)
145 raise ValueError(error_msg)
146
147 def _make_one_branch(self, branch_index, block, num_blocks, num_channels,
148 stride=1):
149 downsample = None
150 if stride != 1 or \
151 self.num_inchannels[branch_index] != (num_channels[branch_index] *
152 block.expansion):
153 downsample = nn.Sequential(
154 nn.Conv2d(self.num_inchannels[branch_index],
155 num_channels[branch_index] * block.expansion,
156 kernel_size=1, stride=stride, bias=False),
157 Norm2d(num_channels[branch_index] * block.expansion,
158 momentum=BN_MOMENTUM),
159 )
160
161 layers = []
162 layers.append(block(self.num_inchannels[branch_index],
163 num_channels[branch_index], stride, downsample))
164 self.num_inchannels[branch_index] = \
165 num_channels[branch_index] * block.expansion
166 for i in range(1, num_blocks[branch_index]):

Callers 1

_make_stageMethod · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected