Skip to content

performance

Performance comparison of PyTorch and Keras3 with TF2 and Torch backends for a small NN-model on a Nvidia 4060 TI – II – Keras with Torch backend

Not all tasks in Machine Learning [ML] require big LLMs or LLM-based interfaces. Actually, many interesting ML-tasks can be solved with neural networks [NNs] that fit well into the VRAM of a modern GPU or TPU affordable even for private persons. This statements holds in particular for image processing. We have groups of people either learning to work with ML… Read More »Performance comparison of PyTorch and Keras3 with TF2 and Torch backends for a small NN-model on a Nvidia 4060 TI – II – Keras with Torch backend

Performance of PyTorch vs. Keras 3 with tensorflow/torch backends for a small NN-model on a Nvidia 4060 TI – I – Torch vs. Keras3/TF2 and relevant parameters

Today’s world of Machine Learning is characterized by competing frameworks. I am used to the combination of Keras with the Tensorflow2 [TF2] backend, but have turned now to using PyTorch in addition. As a beginner with PyTorch, I wanted to get an impression about potential performance advantages in comparison with the Keras/TF2 framework combination. I had read about significant performance… Read More »Performance of PyTorch vs. Keras 3 with tensorflow/torch backends for a small NN-model on a Nvidia 4060 TI – I – Torch vs. Keras3/TF2 and relevant parameters

PyTorch / datasets / dataloader / data transfer to GPU – III – prepared tensor datasets and preloading to GPU

In this post series we have a look at PyTorch dataloaders and Torchvision image datasets (downloaded via PyTorch modules). PyTorch DataLoaders retrieve batches of dataset elements and transfer them to neural networks [NN] on a computation device – e.g. a CUDA driven graphics card. A central dataset functions applies defined transformation operations to its elements. We analyze the impact of… Read More »PyTorch / datasets / dataloader / data transfer to GPU – III – prepared tensor datasets and preloading to GPU

Runtime vs.number of dataloader workers and batch size

PyTorch / datasets / dataloader / data transfer to GPU – II – dataloader too slow on CPU?

Editorial hint: This post has been revised and changed in parts on March, 18th/19th/22nd, 2025, after some new tests and insights. The changes did not concern the result data of the performed experiments, but their interpretation. In the last post of this mini-series we saw that some Torchvision datasets have a directly accessible property “data“. It contains image data in… Read More »PyTorch / datasets / dataloader / data transfer to GPU – II – dataloader too slow on CPU?