The octave-resnet-101-0.125
model is a modification of ResNet-101 with Octave convolutions from Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution with alpha=0.125
. Like the original model, this model is designed for image classification. For details about family of Octave Convolution models, check out the repository.
Metric | Value |
---|---|
Type | Classification |
GFLOPs | 13.387 |
MParams | 44.543 |
Source framework | MXNet* |
Metric | Value |
---|---|
Top 1 | 79.182% |
Top 5 | 94.42% |
A blob that consists of a single image of 1x3x224x224
in RGB
order. Before passing the image blob into the network, subtract RGB mean values as follows: [124,117,104]. In addition, values must be divided by 0.0167.
Image, name: data
, shape: 1,3,224,224
, format: 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: B,C,H,W
, where:
B
- batch sizeC
- channelH
- heightW
- widthChannel order is BGR
.
The model output for octave-resnet-101-0.125
is a typical object-classifier output for 1000 different classifications matching those in the ImageNet database.
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: