Views
No views yet
| Item | Value |
|---|---|
| Architecture | MobileNetV3-Small 100 |
| Source | timm/mobilenetv3_small_100.lamb_in1k |
| Task | Image Classification (1000 cls) |
| Input | 224×224 BGR, uint8→float [0,1] |
| Chip | AX650N (NPU3) |
| Quantization | INT8 |
| Size | 3.3 MB |
| Board | BSP 3.10.2, axengine.InferenceSession |
1import numpy as np
2import axengine
3
4sess = axengine.InferenceSession("model.axmodel")
5data = np.random.rand(1, 3, 224, 224).astype(np.float32)
6out = sess.run(None, {"images": data})
7print(out[0].argmax()) # predicted class