MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like CoordConv.
Say I have the PASCAL VOC dataset, but I want to train a model that only detect sub classes in the dataset, like people, car, does the train script support this? Or I have to manually split(extract only the people and car) the data from dataset?
Hi, thanks for the great repo.
Say I have the
PASCAL VOC
dataset, but I want to train a model that only detect sub classes in the dataset, likepeople
,car
, does the train script support this? Or I have to manually split(extract only thepeople
andcar
) the data from dataset?