I was working with the recently released Tensorflow's API for object detection, with Faster RCNN on Resnet 101 on my own dataset. It seems to train and evaluate on Validation data, but I was hoping if there was a way I could get/store bounding boxes for all images in the Eval set, in a file, or maybe, get the location in the source code where I can get the predicted bounding boxes with image names.
Asked
Active
Viewed 556 times
1 Answers
1
If you just want to obtain the detected bounding boxes given a set of images, the Jupyter notebook contains a good example of how to do this.
Jonathan Huang
- 1,560
- 9
- 12
-
which notebook? – Pablo Gonzalez Aug 18 '17 at 08:32
-
1This is the notebook --- I think it's a pretty good example of how the results should be interpreted: https://github.com/tensorflow/models/blob/master/object_detection/object_detection_tutorial.ipynb – Jonathan Huang Aug 18 '17 at 21:09
-
This link does not exist – Saania Nov 13 '18 at 20:08