Closed ZwkAlex closed 2 years ago
the efficentnet featrure extractor output channels is 512, but inputNode only used the first 304 channels.
This is because we do not use the last convolutional layer, but an intermediate one (index 36). This layer has 304 output channels.
Thanks for the explanation
the efficentnet featrure extractor output channels is 512, but inputNode only used the first 304 channels.