Recently I read a paper. The author implements cifar10 classification task with Caffe and can get 89.9% accuracy.
I can get nearly 94% accuracy using pytorch, and the network structure is the same with the author. We both use pretrianed Alexnet.
I have two questions:
- Can the pretrained Alexnet (trained with ImageNet) make the classification accuracy higher? (I can only get nearly 91% accuracy without pretrained model. But I want to know is this a fact?)
- Is the difference possible when other situations are the same except the framework? And why?