GMU:Computer's Cut/Christian Dähne: Difference between revisions

From Medien Wiki
No edit summary
Line 5: Line 5:


In order to achieve this I trained the yolov5-object-detection-algorithm [https://pytorch.org/hub/ultralytics_yolov5/] with a custom dataset of images of Guitars, Drums, Keyboards, Microphones and Saxophones using fifty one and open images [https://voxel51.com/docs/fiftyone/tutorials/open_images.html]
In order to achieve this I trained the yolov5-object-detection-algorithm [https://pytorch.org/hub/ultralytics_yolov5/] with a custom dataset of images of Guitars, Drums, Keyboards, Microphones and Saxophones using fifty one and open images [https://voxel51.com/docs/fiftyone/tutorials/open_images.html]
[[File:training.jpg]]


I cleaned and prepared the resulting
I cleaned and prepared the resulting detection data using Pandas.
[[File:pandas.jpg]]


==The Essential Mathias Reim==
==The Essential Mathias Reim==
{{#ev:youtube|yGH6nylXflE}}
{{#ev:youtube|yGH6nylXflE}}
MR's hit single from 1990 in a nutshell: "ich", a decent amount of "nicht" paired with a tiny dash of "dich".
MR's hit single from 1990 in a nutshell: "ich", a decent amount of "nicht" paired with a tiny dash of "dich".

Revision as of 21:17, 4 March 2022

Happy Birthday

I made a supercut out of musicvideos of the Top10-SingleCharts from my birthday. The scenes comprise footage in which several instruments are "showcased" visually. I assumed that those scenes would indicate important moments of the referenced composition, like "hooks", solos or other instrumental parts.

In order to achieve this I trained the yolov5-object-detection-algorithm [1] with a custom dataset of images of Guitars, Drums, Keyboards, Microphones and Saxophones using fifty one and open images [2] Training.jpg

I cleaned and prepared the resulting detection data using Pandas. Pandas.jpg

The Essential Mathias Reim

MR's hit single from 1990 in a nutshell: "ich", a decent amount of "nicht" paired with a tiny dash of "dich".