Open ajajar opened 6 years ago
Hi @ljhandlwt understand. Thank you very much.
Also in your init_model function it is specific to your application , it s bit different from the pytorch xnor implementation (alexnet binary part )
Thanks
@ajajar Yes, this is NIN, the same as the implement in cifar-10 of pytorch version, not Alexnet. I don't have enough resource to run the imagenet program, so i give up the implement of Alexnet. However, i think it's easy to update it from NIN to Alexnet, and maybe some additional details should be took care in pytorch version.
Hi @ajajar , Yes, you can train on your custom image after you implement the interface of
Dataset
, includingreset(), get_batch(), is_end()
. However, this work does not work stably and it can't reduce the forward time as it doesn't implement conv by XNOR op.