What is PaddlePaddle?
Joseph NelsonPublished Sep 22, 2021
PaddlePaddle (PArallel Distributed Deep LEarning) is Baidu's open-source deep learning framework, comparable in scope to PyTorch and TensorFlow, providing the core primitives needed to build and train deep learning models. It gained attention in computer vision through PP-YOLO, a model in the YOLO family that improved on YOLOv4 benchmark metrics and is native to the PaddlePaddle framework.
"ML in a Minute" is our conversational series on answering machine learning questions. Have questions you want answered? Tweet at us.
What is PaddlePaddle (in 60 Seconds or Fewer)?
You likely ended up on this post because you Googled "PaddlePaddle machine learning" or "PaddlePaddle Baidu." PaddlePaddle (PArallel Distributed Deep LEarning) is Baidu's – the Chinese equivalent of Google, the search engine – open source machine learning framework. It's similar to PyTorch or TensorFlow. It contains the primitives that you need to implement deep learning models.
PaddlePaddle recently came into the popular eye in computer vision because in the last year there's a new model called PP-YOLO, which is one of the newest models in the YOLO family of models that came after YOLOv5 but before Scaled-YOLOv4. PP-YOLO advanced some state of the art metrics in terms of its comparison to YOLOv4 and even the YOLov5 implementation. PP-YOLO is native to the PaddlePaddle framework.
Liked this? Be sure to also check out the computer vision glossary.
