Open in app

Sign In

Write

Sign In

Pascal Janetzky
Pascal Janetzky

409 Followers

Home

About

Pinned

June’s Reads & Books for July

Carl Honoré, Raymond M. Kethledge & Michael S. Erwin — As in July, two great works came across my reading table. Both books explore two oft-neglected aspects of our lives: being slow and being alone. Enjoy reading them! In Praise of Slowness, by Carl Honoré The world we live in values speed. The untold motto we all unconsciously subscribe to is doing things faster. Getting faster from…

Reading

4 min read

June’s Reads & Books for July
June’s Reads & Books for July
Reading

4 min read


Published in Towards Data Science

·Pinned

A checklist to track your Machine Learning progress

Might have a minimal bias towards Deep Learning — Have you ever asked yourself where you currently are on your Machine Learning journey? And what’s there that you can still learn about? This checklist helps you answer such questions. It provides an outline of the field, divided into three broad levels: Entry level (where everybody starts), intermediate level (where…

Machine Learning

26 min read

A checklist to track your Machine Learning progress
A checklist to track your Machine Learning progress
Machine Learning

26 min read


Published in Towards Data Science

·Pinned

Visualizing Audio Pipelines with Streamlit

Examine the effect of augmentations in your browser — When working with image data, practitioners often use augmentations. Augmentations are techniques that artificially and randomly alter the data to increase diversity. Applying such transformations to the training data makes the model more robust. For image data, frequently used candidates are rotating, resizing, or blurring. The effects of the transformations…

Machine Learning

3 min read

Visualizing Audio Pipelines with Streamlit
Visualizing Audio Pipelines with Streamlit
Machine Learning

3 min read


Published in Towards Data Science

·Pinned

Generative Networks: From AE to VAE to GAN to CycleGAN

A guide to the evolution of generative networks — Introduction In short, the core idea behind generative networks is capturing the underlying distribution of the data. This distribution can not be observed directly, but has to be approximately inferred from the training data. Over the years, many techniques have emerged that aim to generate data similar to the input samples. …

Deep Learning

11 min read

Generative Networks: From AE to VAE to GAN to CycleGAN
Generative Networks: From AE to VAE to GAN to CycleGAN
Deep Learning

11 min read


Published in Towards Data Science

·Mar 2

Storing Images in TensorFlow Record Files

How to use TFRecord files, a TensorFlow-specific data format for efficient data storage and reading, when dealing with images — Did you know that TensorFlow has a custom format to store data? It’s called TensorFlowRecords — or TFRecords for short—and builds upon a simple principle: Store data sequentially (within a file) to access continuous chunks quickly. This approach is based on protocol buffers, a cross-platform approach to storing structural data…

TensorFlow

6 min read

Storing images in TensorFlow record files
Storing images in TensorFlow record files
TensorFlow

6 min read


Published in Towards Data Science

·Jan 31

A pipeline for fast experimentation on Kubernetes

Using native Python packages only — Manually creating a novel configuration file for every new experiment is a tedious process. Especially if you want to rapidly deploy a vast number of jobs on a Kubernetes cluster, an automated setup is a must. With python, it’s straightforward to build a simple scheduling script that reads an experiment’s…

Kubernetes

6 min read

A pipeline for fast experimentation on Kubernetes
A pipeline for fast experimentation on Kubernetes
Kubernetes

6 min read


Published in Towards Data Science

·Jan 23

The smart, flexible way to run code on Kubernetes

When I was a beginner using Kubernetes, my main concern was getting code to run on the cluster. Thrown into a new world, I saw all these confusing YAML-Files, each line and indentation bringing a new meaning. Once I learned the fastest way to get code into the file, I…

Kubernetes

6 min read

The smart, flexible way to run code on Kubernetes
The smart, flexible way to run code on Kubernetes
Kubernetes

6 min read


Published in Towards Data Science

·Jan 9

How to write reproducible TensorFlow input pipelines

Fix the input ordering by using seeds — When preparing machine learning experiments, the input pipeline plays a critical role in data preparation. While they are often straightforward to construct — the machine learning frameworks make this relatively easy —, they lack reproducibility. This is by default: randomness in the input data, such as applying shuffling after each…

Machine Learning

6 min read

How to write reproducible TensorFlow input pipelines
How to write reproducible TensorFlow input pipelines
Machine Learning

6 min read


Nov 19, 2022

When God Gave Me Chocolate

My Ph.D. story: Issue Three — The night before my first tutoring session — with me as a tutor, not as a student — I was very nervous. I conjured up all kinds of questions I could be asked and which I would not know the answers to. I imagined spilling coffee over my materials; I…

Phd Student

5 min read

When God Gave Me Chocolate
When God Gave Me Chocolate
Phd Student

5 min read


Nov 3, 2022

What Correcting Exams Taught Me About What We Do Not Know

My Ph.D. Story: Issue Two — Two months ago, I began my Ph.D. in Machine Learning. To give others a glimpse into this — sometimes far removed — academic world, I created a monthly blog post/newsletter. Through my day-to-day experience in research, I can offer you my unique “hands-on” perspective on academia and related topics. …

PhD

5 min read

What Correcting Exams Taught Me About What Do Not Know
What Correcting Exams Taught Me About What Do Not Know
PhD

5 min read

Pascal Janetzky

Pascal Janetzky

409 Followers

I aim to read, code, and move. pascaljanetzky.com

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech