This is a classical classification network for 1000 classes trained on ImageNet. The difference is that most convolutional layers were replaced by binary ones that can be implemented as XNOR+POPCOUNT operations. Only input, final and shortcut layers were kept as FP32, all the rest convolutional layers are replaced by binary convolution layers.
The quality metrics calculated on ImageNet validation dataset is 61.71% accuracy
|Accuracy top-1 (ImageNet)||61.71%|
A blob with a BGR image in the format: [B, C=3, H=224, W=224], where:
It is supposed that input is BGR in 0..255 range
The output is a blob with the shape [B, C=1000].
[*] Other names and brands may be claimed as the property of others.