Research Article
Performance of Post-Training Two-Bits Uniform and Layer-Wise Uniform Quantization for MNIST Dataset from the Perspective of Support Region Choice
Table 2
SQNR and model accuracy for application of different two-bits LWUQ designs.
| Two-bits LWUQ, accuracy (FP32) = 98.1% |
| (xmaxL1, xmaxL2, xmaxL3) = (4.5150, 4.8371, 3.6784) (xminL1, xminL2, xminL3) = (−7.0638, −5.4354, −6.1979) | Case 1 ℜg | Case 2ℜg | [−xmaxL1, xmaxL1] [−xmaxL2, xmaxL2] [−xmaxL3, xmaxL3] | [xminL1, −xminL1] [xminL2, −xminL2] [xminL3, −xminL3] | SQNRexUQL1 (dB) | 3.1340 | −1.7588 | SQNRexUQL2 (dB) | 3.4507 | 2.2826 | SQNRexUQL3 (dB) | 8.3642 | 4.6137 | SQNRexLWUQ (dB) | 3.3145 | −0.374 | Accuracy (%) | 97.26 | 93.55 |
|
|