The octave-se-resnet-50-0.125
model is a modification of se-resnet-50
from this paper with octave convolutions from Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution with alpha=0.125
. As origin, it's designed to perform image classification. For details about family of octave convolution models, check out the repository.
The model input is a blob that consists of a single image of 1x3x224x224 in RGB order. The RGB mean values need to be subtracted as follows: [124,117,104] before passing the image blob into the network. In addition, values must be divided by 0.0167.
The model output for octave-se-resnet-50-0.125
is the typical object classifier output for the 1000 different classifications matching those in the ImageNet database.
Metric | Value |
---|---|
Type | Classification |
GFLOPs | 7.246 |
MParams | 28.082 |
Source framework | MXNet* |
Metric | Value |
---|---|
Top 1 | 78.706% |
Top 5 | 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 RGB
. Mean values - [124,117,104], scale value - 59.880239521
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: