Use this topic for in-class discussion. Live stream and other links:
Lesson 3 Advanced Discussion:
6 Likes
I’ve noticed that most of the examples and most of my models result in train_loss > valid_loss. What are the best ways to correct that?
I should add that this still happens after trying many variations on # of epochs and lr
18 Likes
Ooops initially misread your > symbol. train > valid is a sign of underfitting and most likely you could train for another epoch or so.
1 Like
actually I’ve run 16-24 epochs in some cases and it rarely seems to get there (meaning to train_loss < valid_loss. I’m referring mainly to lesson 2
1 Like
You should try increasing your learning rate. It must be too small.
1 Like
nope I’ve tried many learning rates also
The FileDeleter still exist in the new library version?
I was running lesson 2 (download images notebook) with the new fastai version and got this error. Does anyone has any idea?
1 Like
I think it is called ImageDeleter now
What version of FastAI are you running?
Questions about nlp Imdb notebook
1- Let’s say I have already prepared train and valid datasets? how to pass them to tokenizer/numericalizer?
2- How to set a different language to the Tokenizer? Like lang=”pt”?
1 Like
version 1.0.21
It is updated with ImageDeleter function
https://forums.fast.ai/t/lesson-2-further-discussion/28706/62?u=win
2 Likes
Is there a repo to contribute to http://videos.fast.ai/?
5 Likes
Password is deeplearningSF2018 (do not share outside the forum group)
9 Likes
Is there a suggested way to to prediction on batches of images? Not from the web but just scripted?
1 Like
But I think @rrmphal is looking for a code repo to contribute.
Is the recommendation for Andrew Ng’s original Coursera course or the new @ deeplearning.ai or both?
2 Likes
The original one
PRs welcome: https://github.com/zcaceres/fastai-video-browser
14 Likes
The fastai ML course covers random forest in detail…can we expect ML part2 covering GBMs?
8 Likes