Inference Time on Extreme Multi-label Classification on AmazonCat-13K
14.4Latency (ms)AttentionXML-1
Evaluation Results
| Method | Links | |
|---|---|---|
| AttentionXML-1GPU=Nvidia V100, batch size=12021.10 | 14.4 | |
| LightXML-1GPU=Nvidia V100, batch size=12021.10 | 24.1 | |
| XR-Transformer-1GPU=Nvidia V100, batch size=12021.10 | 26.1 | |
| X-Transformer-1GPU=Nvidia V100, batch size=12021.10 | 47.6 |