CaffeNet* model is used for classification. For details see paper.
Metric | Value |
---|---|
Type | Classification |
GFlops | 1.463 |
MParams | 60.965 |
Source framework | Caffe* |
Metric | Value |
---|---|
Top 1 | 56.714% |
Top 5 | 79.916% |
Image, name: data
, shape: [1x3x227x227], format: [BxCxHxW] where:
Expected color order: BGR. Mean values: [104.0, 117.0, 123.0].
Image, name: data
, shape: [1x3x227x227], format: [BxCxHxW] where:
Expected color order: BGR.
Object classifier according to ImageNet classes, name: prob
, shape: 1,1000
. Contains predicted probability for each class.
Object classifier according to ImageNet classes, name: prob
, shape: 1,1000
. Contains predicted probability for each class.
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 following license: