Hi @hjiang,
I use Sony's framework [NNabla](https://github.com/sony/nnabla) to train the networks but I then convert them to ONNX or Tensorflow in order to use them with TVM. Accuracy loss gets around 4%. Regards Augusto --- [Visit Topic](https://discuss.tvm.ai/t/vta-first-conv-layer-optimize/6766/4) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/927ea146bff0669acaa83b548c7323cad731c3c52f6c5032c9896acad969dd7c).
