The squeezenet1.1
updated version of the SqueezeNet topology. It is designed to perform image classification. It requires 2.4x less computation than SqueezeNet v1.0 without diminishing accuracy. The SqueezeNet models have been pre-trained on the ImageNet image database. For details about this family of models, check out the repository.
The model input is a blob that consists of a single image of 1x3x227x227 in BGR order. The BGR mean values need to be subtracted as follows: [104, 117, 123] before passing the image blob into the network.
The model output for squeezenet1.1
is the typical object classifier output for the 1000 different classifications matching those in the ImageNet database.
Metric | Value |
---|---|
Type | Classification |
GFLOPs | 0.785 |
MParams | 1.236 |
Source framework | Caffe* |
Metric | Value |
---|---|
Top 1 | 58.382% |
Top 5 | 81% |
Image, name - data
, shape - 1,3,227,227
, format is B,C,H,W
where:
B
- batch sizeC
- channelH
- heightW
- widthChannel order is BGR
. Mean values - [104, 117, 123]
Image, name - data
, shape - 1,3,227,227
, 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: