We've had feedback from multiple developers that it's hard to figure out how to calculate the right int8 values for quantized inputs, and understand what int8 values mean as outputs.

For example, when feeding an image to uint8 quantized inputs, the values can be left as in their source 0 to 255 range. For int8 inputs, the developer will typically need to subtract 128 from each value, but this

In the given documentation, the mentioned key are acc and val_acc, but actually it is accuracy and val_accuracy.

Given documentation screenshot:

Whereas the actual keys are `dict_keys(['val_loss', 'val_accuracy

line 123@
X, Y = read_images(DATASET_PATH, MODE, batch_size)
line 66@
classes = sorted(os.walk(dataset_path).next()[1])
StopIteration

Is there a way Tensorflow git cloned repositories can run without overhead issues?

Current implementation does sequential sigmoid_out and mul_. We can get better performance by fusing this operations together.

Target Leakage in mentioned steps in Data Preprocessing. Train/test split needs to be before missing value imputation. Else you will have a bias in test/eval/serve.

This should really help to keep a track of papers read so far. I would love to fork the repo and keep on checking the boxes in my local fork.

For example: Have a look at this section. People fork this repo and check the boxes as they finish reading each section.

"Bokeh is a Python interactive visualization library that targets modern web browsers for presentation. Its goal is to provide elegant, concise construction of novel graphics in the style of D3.js, but also deliver this capability with high-performance interactivity over very large or streaming datasets. Bokeh can help anyone who would like to quickly and easi

@microsoft AI Team - Fantastic Product! Thank You!

PLEASE: Better documentation on Source Code and Fields, Properties, Methods, and Constructors, just a detailed Summary, please in the C# projects.

When coding, the IntelliSense documentation is very handy! I would really appreciate more detailed documentation.

An example: PreviousMinibatchEvaluationAverage - I have no idea what its ac

I got a conllU file, from my university, where the head column is filled with .
Processing such file with the cli.convert method will result in a int cast error in
https://github.com/explosion/spaCy/blob/master/spacy/cli/converters/conllu2json.py line 73
in the read_conllx method (head = (int(head) - 1) if head != "0" else id).

In the format documentation on https://universaldependencie

transcribe.py has odd directory-scanning behavior which isn't documented

If you point --src to a directory, you get the error:

E Path in --src not existing

Looking at the code logic, the script expects a JSON file with a .catalog file extension. This is (1) not documented, and (2) not a really useful logic. It would be much better to point the script to a dir, and scan f