MLPerf Inference Reference Models

There is a newer version of the record available.

Published January 8, 2019 | Version 0.1
Other Open

resnet50.onnx model

Creators

Description

  • Application: Image Classification
  • ML Task: ResNet-50
  • Framework: ONNX (via tensorflow)
  • Training Information: 
  • Quality: 76.53%
  • Precision: fp32
  • Is Quantized: no
  • Is ONNX: yes
  • Dataset: http://www.image-net.org/challenges/LSVRC/2012/

Notes

How this model was created: ``` download the frozen tensorflow model from https://zenodo.org/deposit/2535873 pip install -U tf2onnx python -m tf2onnx.convert --input resnet50_v1.pb --inputs input_tensor:0 --inputs-as-nchw input_tensor:0 --outputs ArgMax:0 --verbose --opset 8 --output resnet50_v1.onnx ```

Files

Files (102.2 MB)

Name Size Download all
md5:a638cf028b5870da29e09ccc2f7182e7
102.2 MB Download