Image Classification on ImageNet-1k (Accuracy, Model Size, Latency)
81.05AccuracyMCWC (K = 4)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| MCWC (K = 4)Model=Swin-T, bits per model parameter=4.22026.05 | 81.05 | 28 | 0.15 | |
| QAT INT4Model=Swin-T, bits per model parameter=4.32026.05 | 80.2 | 29 | 0.14 |