Become a member
Sign in
Thilo Schmidt
Thilo Schmidt

Thilo Schmidt

4 Following
2 Followers
  • Profile

  • Claps

  • Highlights

Highlighted by Thilo Schmidt

See more

From How to Write an Airflow Operator by Mehmet Vergili

In general if two operators need to share information we should combine them into a single operator. If there is no way to combine them we can use cross communication (XCom) to share information between them.

From Introducing GulpIO by Valentin Haenel

ccess the disk to load samples. For the Kinetics dataset on the othe… dataset on the other hand is around 1 TB. Most of the deep learning compute-resources available at TwentyBN are equipped with around 128 to 512 GB of RAM. This means that ImageNet will easily fit into the file system cache of many of these machines. This means training will be slow during the first epoch. After that, all the images will be cached in memory anyway and you will no longer need to access the disk to load samples. For the Kinetics dataset on the other ha…

From Stop Calling It Intelligence by Meza

What we refer to as AI, has nothing in common with what people believe it to be. Can it solve problems? Yes. Can it recognise patterns? Yes. Can it think? No. Is it intelligent? No.

Claps from Thilo Schmidt

See more

How to Write an Airflow Operator

Mehmet Vergili

For The Love of Cycling — ℤₙ* The Multiplicative group for ℤₙ modulo n

Prof Bill Buchanan OBE

Does Mathematics provide truth?

Descartes’ Demons