ssd300

Use Case and High-Level Description

The ssd300 model is the Caffe* framework implementation of Single-Shot multibox Detection (SSD) algorithm with 300x300 input resolution and VGG-16 backbone. The network intended to perform visual object detection. This model is pretrained on VOC2007 + VOC2012 + COCO dataset and is able to detect 20 PASCAL VOC2007 object classes:

  • Person: person

  • Animal: bird, cat, cow, dog, horse, sheep

  • Vehicle: aeroplane, bicycle, boat, bus, car, motorbike, train

  • Indoor: bottle, chair, dining table, potted plant, sofa, tv/monitor

Mapping model labels to class names provided in <omz_dir>/data/dataset_classes/voc_20cl_bkgr.txt file.

For details about this model, check out the repository.

Example

See here.

Specification

Metric

Value

Type

Detection

GFLOPs

62.815

MParams

26.285

Source framework

Caffe*

Accuracy

The accuracy results were obtained on test data from VOC2007 dataset.

Metric

Value

mAP

87.09%

Input

Original model

Image, name - data, shape - 1, 3, 300, 300, format is B, C, H, W, where:

  • B - batch size

  • C - channel

  • H - height

  • W - width

Channel order is BGR. Mean values - [104.0, 117.0, 123.0]

Converted model

Image, name - data, shape - 1, 3, 300, 300, format is B, C, H, W, where:

  • B - batch size

  • C - channel

  • H - height

  • W - width

Channel order is BGR.

Output

Original model

The array of detection summary info, name - detection_out, shape - 1, 1, 200, 7 in the format 1, 1, N, 7, where N is the number of detected bounding boxes. For each detection, the description has the format: [image_id, label, conf, x_min, y_min, x_max, y_max], where:

  • image_id - ID of the image in the batch

  • label - predicted class ID (1..20 - PASCAL VOC defined class ids). Mapping to class names provided by <omz_dir>/data/dataset_classes/voc_20cl_bkgr.txt file.

  • conf - confidence for the predicted class, in [0, 1] range

  • (x_min, y_min) - coordinates of the top left bounding box corner (coordinates are in normalized format, in range [0, 1])

  • (x_max, y_max) - coordinates of the bottom right bounding box corner (coordinates are in normalized format, in range [0, 1])

Converted model

The array of detection summary info, name - detection_out, shape - 1, 1, 200, 7 in the format 1, 1, N, 7, where N is the number of detected bounding boxes. For each detection, the description has the format: [image_id, label, conf, x_min, y_min, x_max, y_max], where:

  • image_id - ID of the image in the batch

  • label - predicted class ID (1..20 - PASCAL VOC defined class ids). Mapping to class names provided by <omz_dir>/data/dataset_classes/voc_20cl_bkgr.txt file.

  • conf - confidence for the predicted class in [0, 1] range

  • (x_min, y_min) - coordinates of the top left bounding box corner (coordinates are in normalized format, in range [0, 1])

  • (x_max, y_max) - coordinates of the bottom right bounding box corner (coordinates are in normalized format, in range [0, 1])

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>