TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Kaggle’s Yelp Restaurant Photo Classification Competition, Fast.ai Style

73 pointsby harveynickalmost 7 years ago

2 comments

kaveh_halmost 7 years ago
Nick (the author) reflects on this: &quot;The data needs to be merged into a format which can be used to train a neural network. Solving this leads to the second, much bigger issue: many of the resulting label to image mappings are inappropriate...&quot;.<p>If one instead use a RNN (recurrent neural network) particularly with LSTM, then it can take as input the sequence of all photos from a business and the output of the model would then be the sequence of labels, similar to how translation models work. Of course then another problem could perhaps be the ordering of labels is unrelated to order of photos for a business, but there is probably some way to handle this by either data synthesis (multiple permutations of the training data to ignore ordering of labels) or by sorting the labels in a certain fashion that the model can learn.
评论 #17391930 未加载
namuolalmost 7 years ago
I&#x27;d love to see more articles from fast.ai students covering topics other than image (multi) classification. I&#x27;ve been gradually going through the course, and attempting to apply what I&#x27;m learning as I go, but I rarely see good results, especially with structured data.
评论 #17389694 未加载
评论 #17390076 未加载
评论 #17390824 未加载