PyTorch vs. TensorFlow in 2022

This page summarizes the projects mentioned and recommended in the original post on news.ycombinator.com

Our great sponsors
  • InfluxDB - Power Real-Time Data Analytics at Scale
  • WorkOS - The modern identity platform for B2B SaaS
  • SaaSHub - Software Alternatives and Reviews
  • Pytorch

    Tensors and Dynamic neural networks in Python with strong GPU acceleration

    FYI PyTorch now supports "same" padding for convolutions with stride=1; see the docs here: https://pytorch.org/docs/stable/generated/torch.nn.Conv2d.ht...

    The stride>1 case has been a bit more controversial within TensorFlow, and there is ongoing discussion on the correct way to implement it within PyTorch on the issue: https://github.com/pytorch/pytorch/issues/3867

  • jax

    Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

    As a researcher in RL & ML in a big industry lab, I would say most of my colleagues are moving to JAX 0https://github.com/google/jax], which this article kind of ignores. JAX is XLA-accelerated NumPy, it's cool beyond just machine learning, but only provides low-level linear algebra abstractions. However you can put something like Haiku [https://github.com/deepmind/dm-haiku] or Flax [https://github.com/google/flax] on top of it and get what the cool kids are using :)

  • InfluxDB

    Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  • dm-haiku

    JAX-based neural network library

    As a researcher in RL & ML in a big industry lab, I would say most of my colleagues are moving to JAX 0https://github.com/google/jax], which this article kind of ignores. JAX is XLA-accelerated NumPy, it's cool beyond just machine learning, but only provides low-level linear algebra abstractions. However you can put something like Haiku [https://github.com/deepmind/dm-haiku] or Flax [https://github.com/google/flax] on top of it and get what the cool kids are using :)

  • flax

    Flax is a neural network library for JAX that is designed for flexibility.

    As a researcher in RL & ML in a big industry lab, I would say most of my colleagues are moving to JAX 0https://github.com/google/jax], which this article kind of ignores. JAX is XLA-accelerated NumPy, it's cool beyond just machine learning, but only provides low-level linear algebra abstractions. However you can put something like Haiku [https://github.com/deepmind/dm-haiku] or Flax [https://github.com/google/flax] on top of it and get what the cool kids are using :)

  • captum

    Model interpretability and understanding for PyTorch

    Do any JAX experts know if there is an equivalent to https://captum.ai/ - a model interpretability library for pytorch?

    In particular i want to be able to measure feature importance on both inputs and internal layers on a sample by sample basis. This is the only thing currently holding me back from using JAX right now.

    Alternatively a simle to read/understand/port implementation of DeepLIFT would work too.

    thanks

  • DataProfiler

    What's in your data? Extract schema, statistics and entities from datasets

    The thing is, tensorflow has more ability to run cross platform.

    I help maintain https://github.com/capitalone/DataProfiler

    Our sensitive data detection library is exported to iOS, android, and Java; in addition to Python. We also run distributed and federated use cases with custom layers. All of which are improved in tensorflow.

    That said, I’d use pytorch if I could. Simply put, it has a better user experience.

  • ml5-library

    Friendly machine learning for the web! 🤖

    Yeah they made ml5.js for this reason: https://ml5js.org/

    I do feel like Google could do better communicating all of their different tools though. Their ecosystem is large and pretty confusing - they've got so many projects going on at once that it always seems like everyone gets fed up with them before they take a second pass and make them more friendly to newcomers.

    Facebook seems to have taken a much more focused approach as you can see with PyTorch Live

  • WorkOS

    The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.

  • XLA.jl

    Discontinued "Maybe we have our own magic." (by FluxML)

  • nx

    Multi-dimensional arrays (tensors) and numerical definitions for Elixir (by elixir-nx)

  • Flux.jl

    Relax! Flux is the ML library that doesn't make you tensor

NOTE: The number of mentions on this list indicates mentions on common posts plus user suggested alternatives. Hence, a higher number means a more popular project.

Suggest a related project

Related posts