Tensorflow object detection api with weird detection result

1
votes

I have trained tensorflow object detection api on my own dataset with 1 class using rfcn_resnet101 model. Firstly I used the raccoon dataset and trained for 264600 times and the detection result is weird, it can detect the object, but there are some other little boxes around the right box.

Raccoon example

Then I use another dataset containing one class,and there are 80000 images in the dataset, I met the familiar phenomenon. I am very confused.

enter image description here

Have anyone ever met the same situation? What can I do to solve this problem? Thanks in advance!

1
pythontensorflowobject-detection

1 Answers

0
votes

I had the same behavior on the PASCAL VOC Dataset. I haven't fixed it, because I just implemented a model for kind of a proof-of-concept system. My guess is, that the model predicts the proposal regions and accepts them, if there is an IoU greater or equal to an defined threshold. So setting the nms_iou_threshold might solve the problem.

This Adoption also seems to fit your examples. All of the predicted bounding boxes seem to have an IoU with the groundtruth box.