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.
Hi, this is a great repository I am look for! Thanks a lot for your contribution.
I am trying to do a transfer learning from your sq-ssd-lite to learn only detection 3 different object types:
Question might need your help:
could you provide your sq-ssd-lite pretrained model and label URL to allow wget from?
could you give me a hint on how to set the num_classes = 3? that is, make a minor modification of pretrained network then retrain on 3 object types dataset?
Thank you so much for your help.
Hi, this is a great repository I am look for! Thanks a lot for your contribution. I am trying to do a transfer learning from your sq-ssd-lite to learn only detection 3 different object types: Question might need your help: