classy_vision/models/anynet.py [504:536]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            stem_type=StemType[config.get("stem_type", "simple_stem_in").upper()],
            stem_width=config.get("stem_width", 32),
            block_type=BlockType[
                config.get("block_type", "res_bottleneck_block").upper()
            ],
            activation=ActivationType[config.get("activation", "relu").upper()],
            use_se=config.get("use_se", True),
            se_ratio=config.get("se_ratio", 0.25),
            bn_epsilon=config.get("bn_epsilon", 1e-05),
            bn_momentum=config.get("bn_momentum", 0.1),
        )

        return cls(params)

    def forward(self, x, *args, **kwargs):
        x = self.stem(x)
        x = self.trunk_output(x)

        return x

    def init_weights(self):
        # Performs ResNet-style weight initialization
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                # Note that there is no bias due to BN
                fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(mean=0.0, std=math.sqrt(2.0 / fan_out))
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1.0)
                m.bias.data.zero_()
            elif isinstance(m, nn.Linear):
                m.weight.data.normal_(mean=0.0, std=0.01)
                m.bias.data.zero_()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



classy_vision/models/regnet.py [171:203]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            stem_type=StemType[config.get("stem_type", "simple_stem_in").upper()],
            stem_width=config.get("stem_width", 32),
            block_type=BlockType[
                config.get("block_type", "res_bottleneck_block").upper()
            ],
            activation=ActivationType[config.get("activation", "relu").upper()],
            use_se=config.get("use_se", True),
            se_ratio=config.get("se_ratio", 0.25),
            bn_epsilon=config.get("bn_epsilon", 1e-05),
            bn_momentum=config.get("bn_momentum", 0.1),
        )

        return cls(params)

    def forward(self, x, *args, **kwargs):
        x = self.stem(x)
        x = self.trunk_output(x)

        return x

    def init_weights(self):
        # Performs ResNet-style weight initialization
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                # Note that there is no bias due to BN
                fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(mean=0.0, std=math.sqrt(2.0 / fan_out))
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1.0)
                m.bias.data.zero_()
            elif isinstance(m, nn.Linear):
                m.weight.data.normal_(mean=0.0, std=0.01)
                m.bias.data.zero_()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -