[quantizer] Support hybrid Op

[jinevening]

What

Let's support quantization of (TF-style) hybrid Ops whose input feature map is float32 and weights(filters) are quantized.

List of hybrid Ops

• FullyConnected
• Conv2D
• DepthwiseConv2D
• BatchMatMul
• LSTM
• RNN

NOTE This is re-quantization from TF-style quantized model to ONE-style quantized model.