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.
I haven't tried. I am not sure if using "torch.nn.parallel.data_parallel" will be enough. If you can make it work, please feel free to create a pull request. Thanks!
I haven't tried. I am not sure if using "torch.nn.parallel.data_parallel" will be enough. If you can make it work, please feel free to create a pull request. Thanks!
Originally posted by @qfgaohao in https://github.com/qfgaohao/pytorch-ssd/issues/16#issuecomment-439202444