ssd_mobilenet_v1_fpn_coco

Use Case and High-Level Description

MobileNetV1 FPN is used for object detection. For details, see the paper.

Specification

Metric

Value

Type

Detection

GFLOPs

123.309

MParams

36.188

Source framework

TensorFlow*

Accuracy

Metric

Value

coco_precision

35.5453%

Input

Original Model

Image, name: image_tensor, shape: 1, 640, 640, 3, format: B, H, W, C, where:

  • B - batch size

  • H - image height

  • W - image width

  • C - number of channels

Expected color order: RGB.

Converted Model

Image, name: image_tensor, shape: 1, 3, 640, 640, format: B, C, H, W, where:

  • B - batch size

  • C - number of channels

  • H - image height

  • W - image width

Expected color order: BGR.

Output

Original Model

  1. Classifier, name: detection_classes. Contains predicted bounding-boxes classes in range [1, 91]. The model was trained on Common Objects in Context (COCO) dataset version with 91 categories of object, 0 class is for background. Mapping to class names provided in <omz_dir>/data/dataset_classes/coco_91cl_bkgr.txt file.

  2. Probability, name: detection_scores. Contains probability of detected bounding boxes.

  3. Detection box, name: detection_boxes. Contains detection-boxes coordinates in the following format: [y_min, x_min, y_max, x_max], where(x_min, y_min) are coordinates of the top left corner, (x_max, y_max) are coordinates of the right bottom corner.Coordinates are rescaled to an input image size.

  4. Detections number, name: num_detections. Contains the number of predicted detection boxes.

Converted Model

The array of summary detection information, name: DetectionOutput, shape: 1, 1, 100, 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 - ID of the predicted class

  • conf - confidence for the predicted class in range [1, 91], mapping to class names provided in <omz_dir>/data/dataset_classes/coco_91cl.txt file.

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

  • (x_max, y_max) - coordinates of the bottom right bounding box corner (coordinates stored 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>

Use Case and High-Level Description

MobileNetV1 FPN is used for object detection. For details, see the paper.

Specification

Metric

Value

Type

Detection

GFLOPs

123.309

MParams

36.188

Source framework

TensorFlow*

Accuracy

Metric

Value

coco_precision

35.5453%

Input

Original Model

Image, name: image_tensor, shape: 1, 640, 640, 3, format: B, H, W, C, where:

  • B - batch size

  • H - image height

  • W - image width

  • C - number of channels

Expected color order: RGB.

Converted Model

Image, name: image_tensor, shape: 1, 3, 640, 640, format: B, C, H, W, where:

  • B - batch size

  • C - number of channels

  • H - image height

  • W - image width

Expected color order: BGR.

Output

Original Model

  1. Classifier, name: detection_classes. Contains predicted bounding-boxes classes in range [1, 91]. The model was trained on Common Objects in Context (COCO) dataset version with 91 categories of object, 0 class is for background. Mapping to class names provided in <omz_dir>/data/dataset_classes/coco_91cl_bkgr.txt file.

  2. Probability, name: detection_scores. Contains probability of detected bounding boxes.

  3. Detection box, name: detection_boxes. Contains detection-boxes coordinates in the following format: [y_min, x_min, y_max, x_max], where(x_min, y_min) are coordinates of the top left corner, (x_max, y_max) are coordinates of the right bottom corner.Coordinates are rescaled to an input image size.

  4. Detections number, name: num_detections. Contains the number of predicted detection boxes.

Converted Model

The array of summary detection information, name: DetectionOutput, shape: 1, 1, 100, 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 - ID of the predicted class

  • conf - confidence for the predicted class in range [1, 91], mapping to class names provided in <omz_dir>/data/dataset_classes/coco_91cl.txt file.

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

  • (x_max, y_max) - coordinates of the bottom right bounding box corner (coordinates stored 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>

Legal Information

The original model is distributed under the Apache License, Version 2.0. A copy of the license is provided in <omz_dir>/models/public/licenses/APACHE-2.0-TF-Models.txt.