fastbook
fastbook copied to clipboard
fastai
The fastai book, published as Jupyter Notebooks
In the ImageClassifierCleaner(), if I change from cleaning one category (say black bears) to another (grizzly bears), the cleaner instance seems to lose all the changes you’d been flagging for...
Hi, I am using **Google Collab**. I am trying to run section 09_tabular.ipynb fastai/fastbook/blob/master/clean/09_tabular.ipynb and starting from today I have a problem with cont,cat = cont_cat_split(df, 1, dep_var=dep_var) it throws...
value_counts() does not return with a sorted index, hence the plot's labels were random.
This is a silly issue, but this insert from Alexis broke my brain while reading the book (I'm reading the version made of dead trees, but it's still there on...
As seen on Aurélien Geron's Hands-On ML repo (https://github.com/ageron/handson-ml2), I have added links to launch the repo in Google Colab, and Deepnote
The section of the 'Combining Embeddings with Other Methods' says 'This is showing the mean average percent error (MAPE) compared among four different modeling techniques'. I think the meaning of...
https://github.com/fastai/fastbook/blob/master/14_resnet.ipynb ```the number of filters in and out is 4 times higher (256 instead of 64) diminish then restore the number of channels (hence the name bottleneck)``` The word `diminish`...
In the cell which reads: ```python learn = cnn_learner(dls, resnet18, metrics=error_rate) learn.fine_tune(4) ``` I'm getting the warning: ``` /home/jdg/fast.ai.course/fastai-venv/lib/python3.9/site-packages/PIL/Image.py:951: UserWarning: Palette images with Transparency expressed in bytes should be converted...
The word ‘redundent' in the sentence 'Let's try to remove any redundent features', I think should be corrected for ‘redundant'.
Each notebook (both original and clean) starts with a chunk that runs `pip install -Uqq fastbook`. This (silently) causes problems in some environments. For example, I created an environment with...
