alexnet

Use Case and High-Level Description

The alexnet model is designed to perform image classification. Just like other common classification models, the alexnet model has been pretrained on the ImageNet image database. For details about this model, check out the paper.

The model input is a blob that consists of a single image of 1x3x227x227 in BGR order. The BGR mean values need to be subtracted as follows: [104, 117, 123] before passing the image blob into the network.

The model output for alexnet is the usual object classifier output for the 1000 different classifications matching those in the ImageNet database.

Example

Specification

Metric Value
Type Classification
GFLOPs 1.5
MParams 60.965
Source framework Caffe*

Accuracy

Metric Value
Top 1 56.598%
Top 5 79.812%

See the original model's documentation.

Performance

Input

Original model

Image, name - data, shape - 1,3,227,227, format is B,C,H,W where:

Channel order is BGR. Mean values - [104, 117, 123]

Converted model

Original model

Image, name - data, shape - 1,3,227,227, format is B,C,H,W where:

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:

Converted model

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

Legal Information

The original model is distributed under the following license:

This model is released for unrestricted use.