Reg. point 3, Jeremy said that the paper suggests just copying the classes underrepresented to increase their count. I want to experiment with some sort of data augmentation tricks + copying too.
Because the training loss includes dropout. Weāll learn about this soon.
That paper is only relevant to folks with effectively infinite resources. IMHO itās of little if any practical value.
Weāre only using the learning rate finder from that paper, not the cyclical learning rates themselves. The annealing method we use is from https://arxiv.org/abs/1608.03983
Yes, exactly
Yup thatās exactly what weāll be doing
You got it right
Yes thereās dropout. Weāll learn about that soon.
We donāt appear to be using any k-fold cross validation so far. Is this not needed because of TTA?
'+ train prediction through cv
Yes thatās a real issue in the unicorn community. In practice, you have to adjust your probabilities to āundoā the over-sampling.
Yup I did say that. Adding the validation set back in right at the end is fine - you can get a better final model this way. cc @yinterian
Yes, thatās (sort of) what we do for top-down.
Thatās only necessary if you have such a small dataset that you canāt afford to put aside a validation set.
In todayās class, there was a snippet of code:
row_sz, col_sz = list(zip(*size_d.values()))
I understand that *
will unpack the list of dictionary values. Then zip
will pair up the elements of row
, column
tuples to create a list of tuples (the first tuple containing all rows, and the second tuple containing all columns). What I do not understand is the role of list
in this code. Wouldnāt the following do the same?
row_sz, col_sz = zip(*size_d.values())
p.s. I am somewhat new to Python (itās been 4 months), and I have Python for Data Analysis 2nd Edition next to me. So I apologize if this is something obvious.
EDIT: what I wrote is completely wrong! Sorry for the noise.
You would be right in Python 2, but in Python 3 zip
returns an iterator, not a list. So you need to force its evaluation with list
in order to be able to unpack and assign it to row_sz
and col_sz
.
Hi @jacquerie!
Thank you for the response! I do see the zip
returns an iterator. And I guess Iām not fully understanding why this works:
Thanks in advance!
In case you still have issues with the Kaggle command line tool, try refreshing your installed kaggle-cli version because it was updated over the weekend
Iām getting this error in Crestle, do I just need to download that file and unpack the weight files into the right directory? (or do I really need to stop using Crestle?)
learn = ConvLearner.pretrained(arch, data, precompute=True, ps=0.5)
FileNotFoundError Traceback (most recent call last)
ā¦
FileNotFoundError: [Errno 2] No such file or directory: ā/home/nbuser/courses/fastai2/courses/dl1/fastai/weights/resnext_50_32x4d.pthā