I've trained SSD MobileNet v2 model using Tensorflow API on my own dataset of ~4k dog pictures and it displays bounding boxes all over the place. I've trained with batch size 1.
The same dataset trained on faster rcnn works really well, and detects dogs properly.
I've run 50k iterations, and total loss was spiking from 1.5 to 3 all the time in the end, with random bigger spikes, but overall it went down from 20
There wasn't a smooth and gradual decline, but a really spiky and uneven one with both models
Learning graph
I know it's a fast model with low precision, but it should at least more or less detect the object. How can I increase accuracy so it at least partially detects objects without showing completely false bounding boxes ?
Best Answer
You can try adjusting the threshold in the code for inference. Default is 0.5, try out 0.7 or something like that. I have been having the same issue and it works perfectly with the faster RCNN model. Here is an insight – https://github.com/tensorflow/models/issues/3196#issuecomment-359195620
Similar Posts:
- Solved – CorLoc which is used to evaluate object detection performance
- Solved – How to train the RPN in Faster R CNN
- Solved – Multiple object detection where a single image can have multiple objects
- Solved – Object detection – how to annotate negative samples
- Solved – Object detection – how to annotate negative samples