Missing activation layer after DepthwiseConv2D in the bottleneck layer

[VincentChong123]

Thanks for sharing your code!

Compared to attached image from Searching for MobileNetV3, an activation layer (NL) after DepthwiseConv2D seems to be missing from your code below. The code is extracted from _bottleneck() in mobilenet_base.py.

        x = DepthwiseConv2D(kernel, strides=(s, s), depth_multiplier=1, padding='same')(x)
        x = BatchNormalization(axis=channel_axis)(x)
        
        if squeeze:
            x = Lambda(lambda x: x * self._squeeze(x))(x)

[xiaochus]

@weishengchong Thanks for your correction! I put activation function after squeeze module and i will fix it.