The regnetx-3.2gf
model is one of the RegNetX design space models designed to perform image classification. The RegNet design space provides simple and fast networks that work well across a wide range of flop regimes. This model was pretrained in PyTorch*. All RegNet classification models have been pretrained on the ImageNet* dataset. For details about this family of models, check out the Codebase for Image Classification Research.
Metric | Value |
---|---|
Type | Classification |
GFLOPs | 6.3893 |
MParams | 15.2653 |
Source framework | PyTorch* |
Metric | Original model | Converted model |
---|---|---|
Top 1 | 78.15% | 78.15% |
Top 5 | 94.09% | 94.09% |
Image, name - data
, shape - 1,3,224,224
, format is B,C,H,W
where:
B
- batch sizeC
- channelH
- heightW
- widthChannel order is BGR
. Mean values - [103.53,116.28,123.675], scale values - [57.375,57.12,58.395].
Image, name - data
, shape - 1,3,224,224
, format is B,C,H,W
where:
B
- batch sizeC
- channelH
- heightW
- widthChannel order is BGR
Object classifier according to ImageNet classes, name - prob
, shape - 1,1000
, output data format is B,C
where:
B
- batch sizeC
- Predicted probabilities for each class in [0, 1] rangeObject classifier according to ImageNet classes, name - prob
, shape - 1,1000
, output data format is B,C
where:
B
- batch sizeC
- Predicted probabilities for each class in [0, 1] rangeYou 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: