Skip to content

Latest commit

 

History

History
72 lines (46 loc) · 1.6 KB

se-resnet-101.md

File metadata and controls

72 lines (46 loc) · 1.6 KB

se-resnet-101

Use Case and High-Level Description

ResNet-101 with Squeeze-and-Excitation blocks

Example

Specification

Metric Value
Type Classification
GFLOPs 15.239
MParams 49.274
Source framework Caffe*

Accuracy

Metric Value
Top 1 78.252%
Top 5 94.206%

Performance

Input

Original model

Image, name - data, shape - 1,3,224,224, format is B,C,H,W where:

  • B - batch size
  • C - channel
  • H - height
  • W - width

Channel order is BGR. Mean values - [104.0,117.0,123.0].

Converted model

Image, name - data, shape - 1,3,224,224, format is B,C,H,W where:

  • B - batch size
  • C - channel
  • H - height
  • W - width

Channel order is BGR

Output

Original model

Object classifier according to ImageNet classes, name - prob, shape - 1,1000, output data format is B,C where:

  • B - batch size
  • C - Predicted probabilities for each class in [0, 1] range

Converted model

Object classifier according to ImageNet classes, name - prob, shape - 1,1000, output data format is B,C where:

  • B - batch size
  • C - Predicted probabilities for each class in [0, 1] range

Legal Information

The original model is distributed under the Apache License, Version 2.0. A copy of the license is provided in APACHE-2.0-SENet.txt.