Faster R-CNN with Inception Resnet v2 Atrous version. Used for object detection. For details see the paper.
Metric | Value |
---|---|
Type | Object detection |
GFlops | 30.687 |
MParams | 13.307 |
Source framework | TensorFlow* |
Metric | Value |
---|---|
coco_precision | 36.76% |
mAP | 52.41% |
Image, name: image_tensor
, shape: [1x600x1024x3], format: [BxHxWxC], where:
Expected color order: RGB.
image_tensor
, shape: [1x3x600x1024], format: [BxCxHxW], where:Expected color order: BGR.
image_info
, shape: [1x3], format: [BxC], where:detection_classes
. Contains predicted bounding boxes classes in a range [1, 91]. The model was trained on the Microsoft* COCO dataset version with 90 categories of object.detection_scores
. Contains probability of detected bounding boxes.detection_boxes
. Contains detection boxes coordinates in 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.num_detections
. Contains the number of predicted detection boxes.The array of summary detection information, name: reshape_do_2d
, 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 IDconf
- 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])The original model is distributed under the Apache License, Version 2.0. A copy of the license is provided in APACHE-2.0-TensorFlow.txt.