MCPcopy Create free account
hub / github.com/UX-Decoder/Semantic-SAM / MLP

Class MLP

semantic_sam/body/decoder/modules.py:186–198  ·  view source on GitHub ↗

Very simple multi-layer perceptron (also called FFN)

Source from the content-addressed store, hash-verified

184
185
186class MLP(nn.Module):
187 """ Very simple multi-layer perceptron (also called FFN)"""
188
189 def __init__(self, input_dim, hidden_dim, output_dim, num_layers):
190 super().__init__()
191 self.num_layers = num_layers
192 h = [hidden_dim] * (num_layers - 1)
193 self.layers = nn.ModuleList(nn.Linear(n, k) for n, k in zip([input_dim] + h, h + [output_dim]))
194
195 def forward(self, x):
196 for i, layer in enumerate(self.layers):
197 x = F.relu(layer(x)) if i < self.num_layers - 1 else layer(x)
198 return x

Callers 1

__init__Method · 0.70

Calls

no outgoing calls

Tested by

no test coverage detected