This is a TensorFlow* version of densenet-169
model, one of the DenseNet* group of models designed to perform image classification. For details, see TensorFlow* API docs, repository and paper.
Metric | Value |
---|---|
Type | Classification |
GFlops | 6.7932 |
MParams | 14.1389 |
Source framework | TensorFlow* |
Metric | Value |
---|---|
Top 1 | 76.14% |
Top 5 | 93.12% |
Image, name: input_1
, shape: [1x224x224x3], format: [BxHxWxC], where:
B
- batch sizeH
- image heightW
- image widthC
- number of channelsExpected color order: RGB. Mean values - [123.68, 116.78, 103.94], scale values - [58.395,57.12,57.375].
Image, name: input_1
, shape: [1x3x224x224], [BxCxHxW], where:
B
- batch sizeC
- number of channelsH
- image heightW
- image widthExpected color order: BGR.
Object classifier according to ImageNet classes, name - StatefulPartitionedCall/densenet169/predictions/Softmax
, shape - 1,1000
, output data format is B,C
where:
B
- batch sizeC
- Predicted probabilities for each class in [0, 1] rangeThe converted model has the same parameters as the original model.
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:
An example of using the Model Converter:
The original model is distributed under the Apache License, Version 2.0. A copy of the license is provided in APACHE-2.0-TensorFlow.txt.