TQT¶
- class TQT(dtype, enable=True, **kwargs)[source]¶
TQT: https://arxiv.org/abs/1903.08066 Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks.
TQT: https://arxiv.org/abs/1903.08066 Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks.