# efficientdet-d1-tf¶

## Use Case and High-Level Description¶

The efficientdet-d1-tf model is one of the EfficientDet models designed to perform object detection. This model was pre-trained in TensorFlow*. All the EfficientDet models have been pre-trained on the Common Objects in Context (COCO) image database. For details about this family of models, check out the Google AutoML repository.

Metric

Value

Type

Object detection

GFLOPs

6.1

MParams

6.6

Source framework

TensorFlow*

## Accuracy¶

Metric

Converted model

COCO mAP (0.5:0.05:0.95)

37.54%

## Input¶

### Original Model¶

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

• B - batch size

• H - height

• W - width

• C - channel

Channel order is RGB.

### Converted Model¶

Image, name: image_arrays/placeholder_port_0, shape: 1, 640, 640, 3, format is B, H, W, C, where:

• B - batch size

• H - height

• W - width

• C - channel

Channel order is BGR.

## Output¶

### Original Model¶

The array of summary detection information, name: detections, shape: 1, 100, 7 in the format 1, N, 7, where N is the number of detected bounding boxes. For each detection, the description has the format: [image_id, y_min, x_min, y_max, x_max, confidence, label], where:

• image_id - ID of the image in the batch

• (x_min, y_min) - coordinates of the top left bounding box corner

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

• confidence - confidence for the predicted class

• label - predicted class ID, in range [1, 91] across following labels at <omz_dir>/data/dataset_classes/coco_91cl.txt

### Converted Model¶

The array of summary detection information, name: detections, 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 - predicted class ID, in range [0, 90] across following labels at <omz_dir>/data/dataset_classes/coco_91cl.txt

• conf - confidence for the predicted class

• (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])

You can download models and if necessary convert them into OpenVINO™ IR format using the Model Downloader and other automation tools as shown in the examples below.

omz_downloader --name <model_name>
omz_converter --name <model_name>