fastbook
fastbook copied to clipboard
fastai
The fastai book, published as Jupyter Notebooks
In https://github.com/fastai/fastbook/blob/9821dade6e6fb747cc30aceba2923805d5662192/clean/06_multicat.ipynb#L698 I tried https://course.fast.ai/ but haven't found any tutorial. Is it the book [Python for Data Analysis](http://shop.oreilly.com/product/0636920023784.do) by Wes McKinney, the creator of Pandas (O'Reilly)?
Explained here: https://youtu.be/5L3Ao5KuCC4?t=957 This little code snipped can move files to a different category, but as the bears are all numbered files, it will try to move a bear from...
Problem: in the original notebook, the splitting rule results in incorrect train/valid set. Fix: added conditions for splitting + test 
 In chapter 4 notebook, we have the above piece of text. Should the highlighted text instead end with 'before passing it to the function `f`'? In a quick experiment...
This is the error message ``` time: 332.991 Removing intermediate container 285e0ca80f16 The command '/bin/sh -c TIMEFORMAT='time: %3R' bash -c 'time mamba env update -p ${NB_PYTHON_PREFIX} -f "envir onment.yml" &&...
I wasn't quite sure where to report this, as `__init.py__` does not actually seem to appear in this repository (only in the `fastbook` package). Running the notebook for chapter 4,...
Irrespective of potential sarcasm, the probabilities that are referred to in the explanation, `99.6% for "pos" and 0.4% for "neg"`, do not match the code output probabilities `[0.8786, 0.1214]`. 
https://github.com/fastai/fastbook/blob/e57e3155824c81a54f915edf9505f64d5ccdad84/utils.py#L31
Hey, I was just going through the book and found a functions as ```python def binary_cross_entropy(inputs, targets): inputs = inputs.sigmoid() return -torch.where(targets==1, 1-inputs, inputs).log().mean() ``` According to me the function...
When running the Chapter 9 notebook this ValueError is rised: > ValueError: `max_samples` must be in range 1 to 20081 but got value 200000 I suggest changing the max_samples parameter...
