| 指标 | 值 |
|---|---|
| 设备 | Ascend NPU (npu:0) |
| 精度 | float32 |
| Cosine Similarity | 0.999986 |
| Max Absolute Error | 0.000000 |
| NPU 推理时间 | 0.00ms |
python3 inference.py --device npu:0============================================================
模型: cait_xxs24_384_fb_dist
时间: 2026-05-19 11:00:39
设备: Ascend NPU (npu:0)
============================================================
=== cait_xxs24_384.fb_dist_in1k ===
Dtype: torch.float32
--- CPU 推理 ---
输出形状: torch.Size([1, 1000])
输出前5值: [0.032316986471414566, -0.9459549784660339, -1.4142969846725464, -0.4419417977333069, 0.18854635953903198]
推理时间: 796.45ms
--- NPU 推理 ---
输出形状: torch.Size([1, 1000])
输出前5值: [0.03814343735575676, -0.9382968544960022, -1.4101159572601318, -0.4380287826061249, 0.1904868334531784]
推理时间: 18.86ms
=== 精度对比 ===
Cosine Similarity: 0.999982
Max Absolute Error: 0.013493
Relative Error: 0.036011
✓ NPU 适配通过CPU 与 NPU 推理结果对比:
inference.py - NPU 推理脚本report.json - 精度验证报告screenshots/ - 推理输出截图