metadata
language:
- en
MobileNet v1
- Origin: https://github.com/mlcommons/inference/tree/master/vision/classification_and_detection
- Article: https://arxiv.org/abs/1704.04861
- Input:
- size: [N, 3, 224, 224]
- format: NCHW
- ONNX:
- opset: 11
- Operators: 122 (11 types)
- AvgPooling2D: 1
- Clip: 27
- Conv2D: 14
- PaddedConv2D: 1
- PaddedConvDepthWise2D: 13
- Producer: 59
- Reshape: 2
- Shape: 1
- Softmax: 1
- Squeeze: 1
- Cast: 2