efficientnet-b0-pytorch

Use Case and High-Level Description

The efficientnet-b0-pytorch model is one of the EfficientNet models designed to perform image classification. This model was pretrained in PyTorch*. All the EfficientNet models have been pretrained on the ImageNet image database. For details about this family of models, check out the EfficientNets for PyTorch repository.

The model input is a blob that consists of a single image with the [3x224x224] shape in the RGB order. Before passing the image blob to the network, do the following:

  1. Subtract the RGB mean values as follows: [123.675,116.28,103.53]
  2. Divide the RGB mean values by [58.395,57.12,57.375]

The model output for efficientnet-b0-pytorch is the typical object classifier output for 1000 different classifications matching those in the ImageNet database.

Specification

Metric Value
Type Classification
GFLOPs 0.819
MParams 5.268
Source framework PyTorch*

Accuracy

Metric Original model Converted model
Top 1 76.91% 76.91%
Top 5 93.21% 93.21%

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 RGB. Mean values - [123.675,116.28,103.53], scale values - [58.395,57.12,57.375].

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 the logits format

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 the logits format

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-PyTorch-EfficientNet.txt.