Is anyone using scikit for NN? Why/why not?
You should be asking if anyone is using it for ML, not NN.
why?
Scikit-Learn Version 1.0
11–20 of 106 posts
Re: Scikit-Learn Version 1.0
#12Is anyone using scikit for NN? Why/why not?
I have used the MLP classifier[1] before. It's very simple to use (like most of sklearn's models). Worked well for standard and reasonably small classification model, but lacks some features for it to be a flexible way of using NNs: - No saving checkpoints (can be crucial for large models who need alot of compute and time) - No way to assign different activation functions to different layers - No complex nodes like L…
I would say the same as you. As long as you only need a simple model, yes, the MLP is good enough, but forget about making any DeepLearning stuff.
And AFAIK, there isn't GPU support, CPU performance is poor compared to GPU execution.
Re: Scikit-Learn Version 1.0
#13Is anyone using scikit for NN? Why/why not?
NN as in "neural network", or NN as in "nearest neighbour" algorithm? No to the former, yes to the latter. The reason for a "no" to neural networks - in my case I've only ever implemented neural networks with many layers, and typically using kernels, pooling mechanisms, etc, and since scikit-learn doesn't have GPU support, I opt for frameworks that do (PyTorch, TensorFlow). However, if you're only building fully-conn…
GPU can be useful for Nearest Neighbour as well. In case you have access to a GPU, I would strongly recommend Facebook's FAISS [1,2]. For everything else, sklearn is amazing.
[1] https://faiss.ai/ [2] https://github.com/facebookresearch/faiss
Re: Scikit-Learn Version 1.0
#14Scikit-Learn is great, and, reading the documentation for other 3rd party ML packages and seeing the words "Scikit-learn API" is even better.
Re: Scikit-Learn Version 1.0
#15Earlier quoted context omitted.
NN as in "neural network", or NN as in "nearest neighbour" algorithm? No to the former, yes to the latter. The reason for a "no" to neural networks - in my case I've only ever implemented neural networks with many layers, and typically using kernels, pooling mechanisms, etc, and since scikit-learn doesn't have GPU support, I opt for frameworks that do (PyTorch, TensorFlow). However, if you're only building fully-conn…
GPU can be useful for Nearest Neighbour as well. In case you have access to a GPU, I would strongly recommend Facebook's FAISS [1,2]. For everything else, sklearn is amazing. [1] https://faiss.ai/ [2] https://github.com/facebookresearch/faiss
Faiss looks very nice, thanks for the tip!
Re: Scikit-Learn Version 1.0
#16Excellent library for train_test_split.
Jokes aside. This next to Numpy, Pandas Jupyter and Matplotlib + the DL libraries are the reason Python is the powerhouse it is for Data Science.
Re: Scikit-Learn Version 1.0
#17Excellent library with stellar documentation, I hope it'll live on for a long time.
Best documented library. It even provides examples, guidance and best practices in the documentation. Have rarely learned so much as when I went through the sci-kit documentation. Absolute delight.
Re: Scikit-Learn Version 1.0
#18Re: Scikit-Learn Version 1.0
#19Excellent library for train_test_split. Jokes aside. This next to Numpy, Pandas Jupyter and Matplotlib + the DL libraries are the reason Python is the powerhouse it is for Data Science.
I'm with you on sklearn, the DL libraries and Numpy, but Pandas and Matplotlib are poor, poor relations of the tools available in the R ecosystem (dplyr/ggplot etc).
Re: Scikit-Learn Version 1.0
#20Excellent library for train_test_split. Jokes aside. This next to Numpy, Pandas Jupyter and Matplotlib + the DL libraries are the reason Python is the powerhouse it is for Data Science.
I'm with you on sklearn, the DL libraries and Numpy, but Pandas and Matplotlib are poor, poor relations of the tools available in the R ecosystem (dplyr/ggplot etc).
If you're doing data science aren't sklearn, DL, and numpy getting you 90% of the way there anyway? Even if R has better "versions" of pandas/matplotlib (not conceding that point) it's not exactly central to the job of data science.