Skip to content

Latest commit

 

History

History
91 lines (61 loc) · 3.17 KB

README.md

File metadata and controls

91 lines (61 loc) · 3.17 KB

efficientnet-b5-pytorch

Use Case and High-Level Description

The efficientnet-b5-pytorch model is one of the EfficientNet models designed to perform image classification. This model was pre-trained in TensorFlow*, then weights were converted to PyTorch*. All the EfficientNet models have been pre-trained 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 3, 456, 456 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-b5-pytorch is the typical object classifier output for the 1000 different classifications matching those in the ImageNet database.

Specification

Metric Value
Type Classification
GFLOPs 21.252
MParams 30.303
Source framework PyTorch*

Accuracy

Metric Original model Converted model
Top 1 83.69% 83.69%
Top 5 96.71% 96.71%

Input

Original Model

Image, name - data, shape - 1, 3, 456, 456, 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, 456, 456, 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

Download a Model and Convert it into Inference Engine Format

You can download models and if necessary convert them into Inference Engine format using the Model Downloader and other automation tools as shown in the examples below.

An example of using the Model Downloader:

python3 <omz_dir>/tools/downloader/downloader.py --name <model_name>

An example of using the Model Converter:

python3 <omz_dir>/tools/downloader/converter.py --name <model_name>

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.