metadata
datasets:
- ILSVRC/imagenet-1k
metrics:
- accuracy
base_model:
- qualcomm/MobileNet-v3-Small
pipeline_tag: image-classification
tags:
- arxiv:1905.02244
MobileNetv3
Based on https://huggingface.co/qualcomm/MobileNet-v3-Small
Aidge support
Note: We tested this network for the following features. If you encounter any error please open an issue. Features not tested in CI may not be functional.
| Feature | Tested in CI |
|---|---|
| ONNX import | ✔ |
| Backend CPU | ✔ |
Model
- Operators: 234 (14 types)
- Add: 6
- Conv2D: 40
- Div: 1
- FC: 2
- Flatten: 1
- GlobalAveragePooling: 10
- HardSigmoid: 9
- HardSwish: 19
- Mul: 9
- PaddedConv2D: 1
- PaddedConvDepthWise2D: 11
- Producer: 110
- ReLU: 14
- Sub: 1
ImagNet1k
- Opset: 20
- Source: PyTorch
- Input
- size: [N, 3, 224, 224]
- format: [N, C, H, W]
- preprocessing:
- ?
- Output
- size: [N, 1000]