CODEWITHSUNDEEP
tensorflowobject-detection
mr49
mr49

Reputation: 1063

Expected accuracy of the pet example using SSD model in TensorFlow object detection API?

I'm using default pipeline configuration (ssd_inception_v2_pets.config) and pretrained inception v2 COCO model. In TensorBoard, the loss continues decreasing, but the average precision isn't getting any better. Has anyone done similar experiment using inception v2 for SSD? What's your experience?

enter image description here

enter image description here

Upvotes: 2

Views: 1917

Answers (2)

rumbull
rumbull

Reputation: 21

You may have been bitten by this issue: https://github.com/tensorflow/models/issues/2749 as I was.

Try updating & grabbing one of the new starting pretrained files, and seeing if your problem is resolved.

Upvotes: 1

mr49
mr49

Reputation: 1063

The reason of the low mAP is due to extreme low score threshold at non maximum suppression step. The result of such low threshold is that almost every image would produces more than 70 detections, while there's only one ground truth in each image. Changing this threshold to a more reasonable value -- 0.1 -- produces much better mAP plot.

enter image description here

Upvotes: 2

Related Questions