Vict0rsch's blog.

(Deep) Learning Enthusiast

Streaming f1-score in Tensorflow: the multilabel setting

This situation presents 2 challenges: computing an overall f1-score when you only have per-batch values, and doing so in a multilabel setting where micro, macro and weighted f1 scores are expected. What a journey!

Written By
Victor Schmidt

Sampling a multilabel dataset

Splitting a multi-label dataset into train and test sets is more complicated than the single-label case. You can't simply split each class. You have to be more clever, and stratify - here's how.

Written By
Victor Schmidt

Save and Restore a Tensorflow model with its Dataset using simple_save

The saved_model API allows for easy saving. Restoring the model and performing inference is a bit trickier when the input Tensors come from a tf.data.Dataset. We'll see here how this works.

Written By
Victor Schmidt

MacOS Terminal and Shell Setup with configuration files

That's my personal setup: links, descriptions and configuration. From ZSH to Pyenv through Spaceship and Tmux

Written By
Victor Schmidt

AWS AMI for p2 instances with Tensorflow 1.0

Here is my second AMI, ugraded from the previous one with a lot of what you need

Written By
Victor Schmidt

‹ Newer Older ›