Hier werden die Unterschiede zwischen zwei Versionen angezeigt.
| Nächste Überarbeitung | Vorhergehende Überarbeitung | ||
| deep_learning [2020/06/10 16:10] – angelegt gerald | deep_learning [2024/02/29 13:36] (aktuell) – Externe Bearbeitung 127.0.0.1 | ||
|---|---|---|---|
| Zeile 1: | Zeile 1: | ||
| + | |||
| + | |||
| + | Beste Grafikkarten GPUs: [[https:// | ||
| + | |||
| + | Machine Learning | ||
| + | |||
| + | Artificial Intelligence | ||
| + | |||
| + | Machine Learning Maschine Learning | ||
| + | |||
| + | |||
| + | Unterschiede Gehirn neuronales Netz | ||
| + | https:// | ||
| + | |||
| + | |||
| + | {{:: | ||
| + | |||
| + | ====== Neuronale Netzwerke ====== | ||
| + | Einführung Videos (engl.): [[https:// | ||
| + | Einführung (Kostenloses Buch, engl.): [[http:// | ||
| + | |||
| + | |||
| + | * Parameter: Anzahl der Neuronen (Parameter: Bias/ | ||
| + | * Aktivierungsfunktion: | ||
| + | ====== Fertig trainierte KI-Netzerke ====== | ||
| + | |||
| + | ===== Grafik ===== | ||
| + | Videos online erstellen kostenlos: https:// | ||
| + | ===== Text ===== | ||
| + | |||
| + | [[https:// | ||
| + | |||
| + | Frei: | ||
| + | |||
| + | [[https:// | ||
| + | |||
| + | [[https:// | ||
| ====== Deep Learning ====== | ====== Deep Learning ====== | ||
| + | |||
| + | Crash course Google : https:// | ||
| Zeile 12: | Zeile 51: | ||
| [[http:// | [[http:// | ||
| - | PyTorch | ||
| - | ===== TensorFlow | + | ===== OpenCV |
| + | ==== Beispiele ==== | ||
| + | |||
| + | |||
| + | === Vorbeifahrende Autos zählen === | ||
| + | |||
| + | |||
| + | Object tracking in video with OpenCV and Deep Learning ((https:// | ||
| + | |||
| + | Pattern: [[https:// | ||
| + | |||
| + | Repo: [[https:// | ||
| + | |||
| + | |||
| + | ===== Frameworks ===== | ||
| + | |||
| + | |||
| + | |||
| + | |||
| + | ==== PyTorch ==== | ||
| + | |||
| + | ==== TensorFlow ==== | ||
| + | |||
| + | |||
| + | [[https:// | ||
| [[https:// | [[https:// | ||
| + | ==== Keras ==== | ||
| + | |||
| + | Grundlagen: [[https:// | ||
| + | |||
| + | |||
| + | ==== DL4J ==== | ||
| + | |||
| + | |||
| + | ==== Caffee ==== | ||
| + | |||
| + | |||
| + | ==== Microsoft Recognition Toolkit ==== | ||
| + | |||
| + | ===== YOLO ===== | ||
| + | |||
| + | You only look once | ||
| + | |||
| + | Quelle((https:// | ||
| + | |||
| + | |||
| + | You Only Look Once - this object detection algorithm is currently the state of the art, outperforming R-CNN and it's variants. I'll go into some different object detection algorithm improvements over the years, then dive into YOLO theory and a programmatic implementation using Tensorflow! | ||
| + | |||
| + | Code for this video: | ||
| + | https:// | ||
| + | |||
| + | More learning resources: | ||
| + | https:// | ||
| + | |||
| + | https:// | ||
| + | |||
| + | http:// | ||
| + | |||
| + | https:// | ||
| + | |||
| + | https:// | ||
| + | |||
| + | https:// | ||
| + | |||
| + | https:// | ||