Hi @leaderj1001 ,
I have an error when i tested your model with input_size is an even multiple of 32 such as (512 x 512, 448 x 448) but don't have this error with input_size is an odd multiple of 32 like 224x 224, 416 x 416.
How can I fix that ?
Have you trained MixNet models for Cifar-10 from scratch (not transfer learning from ImageNet models)?
With default configuration, I obtain about 70% accuracy for MixNet small, and the accuracy decreases as the model size increases. Do I need to change some particular parameters in the configuration while training Cifar-10?