hbonet-0.5¶
Use Case and High-Level Description¶
The hbonet-0.5
model is one of the classification models from repository with width_mult=0.5
Specification¶
Metric |
Value |
---|---|
Type |
Classification |
GFLOPs |
0.096 |
MParams |
2.5289 |
Source framework |
PyTorch* |
Accuracy¶
Metric |
Original model |
---|---|
Top 1 |
67.00% |
Top 5 |
86.90% |
Input¶
Original Model¶
Image, name: input
, shape: 1, 3, 224, 224
, format: B, C, H, W
, where:
B
- batch sizeC
- number of channelsH
- image heightW
- image widthExpected color order:
RGB
. Mean values: [123.675, 116.28, 103.53], scale factor for each channel: [58.395, 57.12, 57.375]
Converted Model¶
Image, name: input
, shape: 1, 3, 224, 224
, format: B, C, H, W
, where:
B
- batch sizeC
- number of channelsH
- image heightW
- image width
Expected color order: BGR
.
Output¶
Object classifier according to ImageNet classes, shape: 1, 1000
in B, C
format, where:
B
- batch sizeC
- vector of probabilities for all dataset classes.
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 <omz_dir>/models/public/licenses/APACHE-2.0.txt
.