course22
course22 copied to clipboard
fastai
The fast.ai course notebooks
learn.predict no longer takes a PILImage as per [1]. Replace with path to the image. [1]: https://www.kaggle.com/discussions/getting-started/389456#2155959
Trying to work through Ch1 in Colab, the training of the cat recognition model has taken up to 40 minutes per epoch and some error messages about deprecated variable names....
In the notebook named "How does a neural net really work?", there is a point where the parameters of a parabola are found using gradients. There is a cell with...
Hi Jeremy, I just wanted to let you know that the Hugging Face Pet Breed Classifier is broken. I think it is a problem with Gradio
Not sure if this is the place to file comments about resources for the course, but just wanted to relay my experience. I came here via the book > website...
Ref: https://www.kaggle.com/discussions/getting-started/389456#2155959
you have a broken link in book https://colab.research.google.com/github/fastai/fastbook/blob/master/01_intro.ipynb#scrollTo=Dstgb90CFeyc "The second line downloads a standard dataset from the [fast.ai datasets collection](https://course.fast.ai/datasets) (if not previously downloaded) to your server, extracts it (if...
For lesson 05-linear-model-and-neural-net-from-scratch.ipynb the above command gives an exception (KeyError: 5) on kaggle. Need to use .values as df.Survived.values for this to work correctly. Kindly update. Thanks
is_bird,_,probs = learn.predict(PILImage.create('bird.jpg')) errors out with (ultimately) AttributeError: read. Notebook with full stacktrace here: https://www.kaggle.com/code/danwashceros/is-it-a-bird-creating-a-model-from-your-own-data
The test images (downloaded at the beginning of the lesson) are sometimes re-downloaded and used in the training set. I have suggested a simple fix (discard the training image if...
