VOC with Fewer Classes - Githubissues

amdegroot / ssd.pytorch

A PyTorch Implementation of Single Shot MultiBox Detector

MIT License

5.15k stars 1.75k forks source link

VOC with Fewer Classes #560

Open bspivey opened 3 years ago

bspivey commented 3 years ago

How can we train on fewer classes with the VOC dataset? I have changed the VOC_CLASSES dictionary to two labels and updated cfg['num_classes'] to 3, yet I still see the algorithm looking for other labels.

ksmdnl commented 2 years ago

I think in this case you have to either adjust the training labels or generate new training labels with only the desired classes