Jeremy from fast.ai here. Let me know if you have any questions about the methods we used, or anything else relevant to this project.
Does the solution use pre trained Resnet models?
Findings from the Imagenet and CIFAR10 competitions
11–19 of 19 posts
Re: Findings from the Imagenet and CIFAR10 competitions
#12Re: Findings from the Imagenet and CIFAR10 competitions
#13Earlier quoted context omitted.
Does the solution use pre trained Resnet models?
No you can't use pre-trained models in this competition.
Thanks for the prompt response. Do you use data augmentation? Sorry for all the questions which could maybe be answered by looking at the code, but I am just getting started with pytorch etc and I am trying to understand the exact input format.
Re: Findings from the Imagenet and CIFAR10 competitions
#14Jeremy from fast.ai here. Let me know if you have any questions about the methods we used, or anything else relevant to this project.
How important was momentum cycle (The decrease then increase)?
Unrelated but it would be great if you could answer: In general, how important is momentum tuning and what are the heuristics for the same?
Re: Findings from the Imagenet and CIFAR10 competitions
#15Jeremy from fast.ai here. Let me know if you have any questions about the methods we used, or anything else relevant to this project.
How important was momentum cycle (The decrease then increase)?
Unrelated but it would be great if you could answer: In general, how important is momentum tuning and what are the heuristics for the same?
Re: Findings from the Imagenet and CIFAR10 competitions
#16Jeremy from fast.ai here. Let me know if you have any questions about the methods we used, or anything else relevant to this project.
Is the code used for the competition available?
Re: Findings from the Imagenet and CIFAR10 competitions
#17Jeremy from fast.ai here. Let me know if you have any questions about the methods we used, or anything else relevant to this project.
Is the code used for the competition available?
Yes it's linked from the competition web site. It'll be integrated into the fastai library in the coming weeks.
Re: Findings from the Imagenet and CIFAR10 competitions
#18Earlier quoted context omitted.
No you can't use pre-trained models in this competition.
Thanks for the prompt response. Do you use data augmentation? Sorry for all the questions which could maybe be answered by looking at the code, but I am just getting started with pytorch etc and I am trying to understand the exact input format.
Yes data augmentation is critical
Re: Findings from the Imagenet and CIFAR10 competitions
#19Jeremy from fast.ai here. Let me know if you have any questions about the methods we used, or anything else relevant to this project.
How important was momentum cycle (The decrease then increase)? Unrelated but it would be great if you could answer: In general, how important is momentum tuning and what are the heuristics for the same?
Based on Smith's paper and our experiments, it seems pretty important. But there's still much research to be done to understand momentum tuning and related concepts.