mobilenet-v3-small-1.0-224-tf
is one of MobileNets V3 - next generation of MobileNets, based on a combination of complementary search techniques as well as a novel architecture design. mobilenet-v3-small-1.0-224-tf
is targeted for low resource use cases. For details see paper.
Metric | Value |
---|---|
Type | Classification |
GFlops | 0.121 |
MParams | 2.537 |
Source framework | TensorFlow* |
Metric | Original model | Converted model |
---|---|---|
Top 1 | 67.36% | 67.36% |
Top 5 | 87.45% | 87.45% |
Image, name: input
, shape: [1x224x224x3], format: [BxHxWxC], where:
- B - batch size - H - image height - W - image width - C - number of channels
Expected color order: RGB. Mean values: [127.5, 127.5, 127.5], scale factor for each channel: 127.5
Image, name: input
, shape: [1x3x224x224], format: [BxCxHxW], where:
- B - batch size - C - number of channels - H - image height - W - image width
Expected color order: BGR.
Probabilities for all dataset classes (0 class is background). Name: MobilenetV3/Predictions/Softmax
, shape: [1,1001], format: [BxC], where:
Probabilities for all dataset classes (0 class is background). Name: MobilenetV3/Predictions/Softmax
, shape: [1,1001], format: [BxC], where:
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-TF-Models.txt.