googlenet-v3 model is the first of the Inception family of models designed to perform image classification. For details about this family of models, check out the paper.
input, shape: [1x299x299x3], format: [BxHxWxC], where:
Expected color order: RGB. Mean values: [127.5, 127.5, 127.5], scale factor for each channel: 127.5
input, shape: [1x3x299x299], format: [BxCxHxW], where:
Expected color order: BGR.
Object classifier according to ImageNet classes, name:
InceptionV3/Predictions/Softmax, shape: [1,1001] in [BxC] format, where:
- B - batch size - C - vector of probabilities for all dataset classes (0 class is background). Probabilities are represented in logits 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:
An example of using the Model Converter: