Mask R-CNN Resnet50 Atrous trained on COCO dataset. It is used for object instance segmentation. For details, see the paper.
Metric | Value |
---|---|
Type | Instance segmentation |
GFlops | 294.738 |
MParams | 50.222 |
Source framework | TensorFlow* |
Metric | Value |
---|---|
coco_orig_precision | 29.7512% |
coco_orig_segm_precision | 27.4597% |
Image, name: image_tensor
, shape: [1x800x1365x3], format: [BxHxWxC],
where:
- B - batch size
- H - image height
- W - image width
- C - number of channels
Expected color order: RGB.
-
Image, name:
image_tensor
, shape: [1x3x800x1365], format: [BxCxHxW], where:- B - batch size
- C - number of channels
- H - image height
- W - image width
Expected color order: BGR.
-
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)
- Classifier, name:
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 objects, 0 class is for background. - Probability, name:
detection_scores
. Contains probability of detected bounding boxes. - Detection box, name:
detection_boxes
. 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. - Detections number, name:
num_detections
. Contains the number of predicted detection boxes. - Segmentation mask, name:
detection_masks
. Contains segmentation heatmaps of detected objects for all classes for every output bounding box.
-
The array of summary detection information, name:
reshape_do_2d
, shape: [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 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])
-
Segmentation heatmaps for all classes for every output bounding box, name:
masks
, shape: [N, 90, 33, 33], where N is the number of detected masks, 90 is the number of classes (the background class excluded).
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.