RetinaNet is the dense object detection model with ResNet50 backbone, originally trained on Keras*, then converted to TensorFlow* protobuf format. For details, see paper, repository.
47fdf189
commit)keras_to_tensorflow.patch
: Metric | Value |
---|---|
Type | Object detection |
GFlops | 238.9469 |
MParams | 64.9706 |
Source framework | TensorFlow* |
Metric | Value |
---|---|
coco_precision | 33.15% |
Image, name: input_1
, shape: [1x1333x1333x3], format: [BxHxWxC], where:
Expected color order: BGR. Mean values: [103.939, 116.779, 123.68]
Image, name: input_1
, shape: [1x3x1333x1333], format: [BxCxHxW], where:
Expected color order: BGR.
filtered_detections/map/TensorArrayStack_2/TensorArrayGatherV3
. Contains predicted bounding boxes classes in a range [1, 80]. The model was trained on the Microsoft* COCO dataset version with 80 categories of objects, 0 class is for background. Mapping to class names provided in <omz_dir>/data/dataset_classes/coco_80cl_bkgr.txt
filefiltered_detections/map/TensorArrayStack_1/TensorArrayGatherV3
. Contains probability of detected bounding boxes.filtered_detections/map/TensorArrayStack/TensorArrayGatherV3
. Contains detection boxes coordinates in a 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 input image size.The array of summary detection information, name - DetectionOutput
, 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 in range [1, 80], mapping to class names provided in <omz_dir>/data/dataset_classes/coco_80cl_bkgr.txt
fileconf
- confidence for the predicted classx_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 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 Apache License, Version 2.0. A copy of the license is provided in APACHE-2.0.txt.