Walkthru 15 a rough detailed note in the form of questions and images
Built upon very nice video timeline by @mattr and @kurianbenoy
02:00 - Can we sleep while GPU is working on the models without losing everything in the morning
04:00 - Connecting to your server using Xrdp
07:00 - Can you connect to Paperspace machines remotely?
06:30 - Installing Xrdp
13:30 - Dealing with startup issue in Paperspace
15:52 Can we sleep and let paperspace working on? (paid user should be ok)
16:20 - Native windows in tmux with
tmux -CC a
18:30 - Getting mouse support working in tmux
20:00 - Experimenting with closing notebooks while fine tuning
24:30 How to use a extra large model to apply progressive resizing?
How does ( with halved learning rate) Gradient accumulation can help you train with bigger images with less time?
Why do we need to set gradient accumulation to 4 on Kaggle instead of 2 on Jeremy’s computer?
26:00 - Building a model with weighted training set
duplicate Road to top 2 notebook for weighted model 28:15
32:35 Students said applying the techniques like confusion matrix etc learned in lecture 1-2 for paddy has not been easy
33:10 Why or when should we use
weighted_dataloaders to a dataset
hint: some classes are harder; or some are less common
33:33 How to create the weights for data to show less common ones more often and vice verse in both a dramatic method and less dramatic method?
34:40 Do we face the danger of overfitting model trained with weighted dataset to think the less common classes are more common? yes
36:14 How to give weights to each item based on the item’s class/disease names (including the weights into the dataframe of
37:41 According to where
WeightedDataLoader is defined, we have to build a
DataBlock first, and then create a
42:41 How Jeremy figure out the way to use
Weighted_dataloaders using docs and source?
43:49 How to map the dataframe where weights are stored to the files returned from
How Jeremy used a lazier method (sorting) to do the mapping above? 44:46?
46:52 How Jeremy explore and experiment to make
Weighted_dataloaders work in real time?
47:48 How did Jeremy explore and experiment to force
Datasets.weighted_dataloaders to apply
item_tfms which are actually used only happen in
55:04 How to use pdb to debug an error directly? (weights should only include training set not validation set)
h: for help
w: where in the stack you are in
p self.n: to print out
q: to exit
What exactly is the problem?
56:30 How to pick out weights only for the training set using pandas index func?
MISSING IMAGE: good-mix
1:00:55 How the batch is created in weighted dataset?
hint: a 64 images are sampled from a dataset weighted by the weights, not the normal dataset
What does model on weighted dataset see in one epoch?
no longer the full dataset once, but a lot more less-common items, so overfitting is a danger
Why we should expect the error rate of weighted model to be worse?
1:02:26 When to use weighted dataset to train the model is more appropriate?
you could train the model well with proper dataset enough times and then use weighted dataset to train only a few epochs
other ways of using weighted dataset?
1:03:24 How should
1:03:54 How to fix up
weighted_dataloaders and update the fastai library?
git pull to get the latest fastai lib
step 2: go to
fastai/nbs/14a_callback.data.ipynb and find
step 3: make changes
Weighted_dataloaders a callback?
it is a
dataloader and a patch to a
1:05:32 How does
@patch add a method/function
weighted_dataloaders to a class
1:06:02 How to create a
DataBlock class and another
1:09:23 How doe
@delegates(Datasets.dataloaders) pass all its parameters to
return self.dataloaders(....) and then to
1:09:47 How to create/fix the tests
1:13:23 How to export and try out the updated fastai lib?
How to export the library?
How update and use the new lib locally?
1:14:37 How Jeremy would like splitter to work nicely with
1:17:56 How does splitter work inside
Datasets to split training and validation sets
The final version of
Now, it all works
1:23:24 run test and create an issue about updating lib
How to run test?
What’s the error in the test of
How to create an issue from terminal?
#question where are Jeremy’s dotfiles?
1:24:33 To fix the test error by converting a list into an np.array when wgts is a list
How to check whether
wgts is a Tensor or np.array with
How to update or fix the issue
1:29:58 How to use nbdev hook to clean notebooks