I have made some small updates to the blog post, with some extra details on git-lfs
installation, API usage, etc… check it out!
If you ever get around to it, a nice add would be adding a section called: “What to do with git-lfs
goes wrong”
I messed something up with adding files to git-lfs
and was getting errors I couldn’t resolve around “missing” files. Ended up just cloning the HF Spaces repo and starting from scratch. Heck, that might be the answer, haha.
That’s my approach too…
thankfully, if it all goes wrong with ifs, at least files can be uploaded via the Spaces UI. “Add files” button.
For the homework to read the book, I had to muddle around a bit to get 01_intro.ipynb running smoothly on kaggle.com. So I’m documenting here in case it helps anyone, and I might learn from others suggesting improvements.
-
Log in to kaggle.com
-
Choose…
-
Create new notebook…
-
File > Import Notebook…
(note, I did earlier do “Link to github”, but I don’t think that was required.) -
Click the github icon, search for fastbook, select fastai/fastbook,
then choose the required chapter and click the Import button.
-
The first cell was producing the shown error. Removing the red boxed code made it work (I’m not sure of any negative impact).
-
Images were not appearing, showing as placeholder icons
saw it was defined like this…
Changing the first cell as follows makes it all work…
(may need to reload browser page)
What do you think about Jupyter Lab? Seems like we mostly use Jupyter Notebooks in the course. I was thinking that the former one is about to become an improved version of the latter. But I guess it didn’t become a ubiquitous approach.
For anyone new to jupyter notebooks-a writeup about useful extensions might be an awesome weekend project
Do all these extend to jupyter lab?
I use Jupyter Lab extensively and like it a lot actually… Gives me more of an IDE feel that I like I guess…
Is there a some kind of auto-augmentation in fastai? (Sorry if this was mentioned somewhere already.) Last time I tried this approach in some other framework, it wasn’t easy to set up.
Update
I mean, something like a backprop guided augmentations derived from the data. But I guess it is not relevant for this lesson anyway, something to ask about in a different thread.
Do you mean distinct from what Jeremy is explaining in the live course right now re RandomResizedCrop
and aug_transforms
option?
At what point do you add more data to the dataset? Ie if the model had trouble identifying multiple teddy bears, do you immediately add more images of that?
@Raymond-Wu This really depends on what you’re trying to accomplish. In general, adding more data helps if you have already chosen a good underlying neural net architecture to work on your problem.
Does anyone know what the best bang for buck GPUs are on GCP? I picked a T4 because its got lots of ram and the price is pretty similar to the P4. I was under the impression the older K80s aren’t that fast for the price. If i’m going to pay for one on the lower end what does everyone recommend?
Putting this question here from the chat: If you went looking for photos of grizzlys and black bears online (assuming there wasn’t a dataset already made and labelled), what is the best way to ensure these photos aren’t misclassified?.
Jeremy then showed the Image Classifier Cleaner, and Nick said it pays to visually inspect when using these “open” image searches. Results can deteriorate drastically with both the inherent ambiguity of your topic or your search query. Sheik Mohamed Imran said we would have to manually get the losses for the data and sort it.Or you van peek into the code used for the GUI, has the same logic
I think Albumentations has something like this:
You might be able to run this, get your augmentation policy, and incorporate it in fastai like this:
But I haven’t tried this… could be something interesting to play around with
Yes, exactly, that’s another framework I was talking about
Somehow, it was difficult to integrate this (autoaug) into my pipeline last time I tried it out. However, maybe it was just me. However, otherwise, the lib is great and a default way to go with augmentations for many projects.