Use Case and High-Level Description

Faster R-CNN Resnet-50 model. Used for object detection. For details, see the paper.



Metric Value
Type Object detection
GFlops 57.203
MParams 29.162
Source framework TensorFlow*


Metric Value
coco_precision 27.47%



Original Model

Image, name: image_tensor, shape: [1x600x1024x3], format: [BxHxWxC], where:

Expected color order: RGB.

Converted Model

  1. Image, name: image_tensor, shape: [1x3x600x1024], format: [BxCxHxW], where:
    • B - batch size
    • C - number of channels
    • H - image height
    • W - image width

Expected color order: BGR.

  1. Information of input image size, name: image_info, shape: [1x3], format: [BxC], where:
    • B - batch size
    • C - vector of 3 values in format [H,W,S], where H is an image height, W is an image width, S is an image scale factor (usually 1).


Original Model

  1. Classifier, name: detection_classes. Contains predicted bounding boxes classes in a range [1, 91]. The model was trained on Microsoft* COCO dataset version with 90 categories of objects.
  2. Probability, name: detection_scores. Contains probability of detected bounding boxes.
  3. Detection box, name: detection_boxes. Contains detection boxes coordinates in format [y_min, x_min, y_max, x_max], where (x_min, y_min) are coordinates top left corner, (x_max, y_max) are coordinates right bottom corner. Coordinates are rescaled to 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: 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:

Legal Information

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.