The ssd512
model is the Caffe* framework implementation of Single-Shot multibox Detection (SSD) algorithm with 512x512 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 VOC2012 object classes:
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.
See here.
Metric | Value |
---|---|
Type | Detection |
GFLOPs | 180.611 |
MParams | 27.189 |
Source framework | Caffe* |
The accuracy results were obtained on validation data from VOC2012 dataset.
Metric | Value |
---|---|
mAP | 90.3845% |
Image, name - data
, shape - 1,3,512,512
, format is B,C,H,W
where:
B
- batch sizeC
- channelH
- heightW
- widthChannel order is BGR
. Mean values - [104.0,117.0,123.0]
Image, name - data
, shape - 1,3,512,512
, format is B,C,H,W
where:
B
- batch sizeC
- channelH
- heightW
- widthChannel order is BGR
.
The array of detection summary info, name - detection_out
, shape - 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 batchlabel
- 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] rangex_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])The array of detection summary info, name - detection_out
, shape - 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 batchlabel
- 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] rangex_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])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:
An example of using the Model Converter:
The original model is distributed under the following license: