Skip to main content
TrustRadius
Pytorch

Pytorch

Overview

What is Pytorch?

Pytorch is an open source machine learning (ML) framework boasting a rich ecosystem of tools and libraries that extend PyTorch and support development in computer vision, NLP and or that supports other ML goals.

Read more
Recent Reviews

TrustRadius Insights

Easy to use: Users have consistently found PyTorch to be one of the easiest deep learning frameworks, with a simple model definition and …
Continue reading

Pytorch in a nutshell

10 out of 10
August 26, 2022
Incentivized
We are using Pytorch to construct computer vision Deep Learning models for a battery of projects in the Data Platform project pipeline. …
Continue reading
Read all reviews
Return to navigation

Pricing

View all pricing
N/A
Unavailable

What is Pytorch?

Pytorch is an open source machine learning (ML) framework boasting a rich ecosystem of tools and libraries that extend PyTorch and support development in computer vision, NLP and or that supports other ML goals.

Entry-level set up fee?

  • No setup fee

Offerings

  • Free Trial
  • Free/Freemium Version
  • Premium Consulting/Integration Services

Would you like us to let the vendor know that you want pricing?

15 people also want pricing

Alternatives Pricing

What is Qlik Sense?

Qlik Sense® is a self-service BI platform for data discovery and visualization. It supports a full range of analytics use cases—data governance, pixel-perfect reporting, and collaboration. Its Associative Engine indexes and connects relationships between data points for creating actionable insights.

What is Databricks Lakehouse Platform?

Databricks in San Francisco offers the Databricks Lakehouse Platform (formerly the Unified Analytics Platform), a data science platform and Apache Spark cluster manager. The Databricks Unified Data Service aims to provide a reliable and scalable platform for data pipelines, data lakes, and data…

Return to navigation

Product Demos

Video Demo with PixelLib Pytorch version using PointRend for instance segmentation.

YouTube

Deep learning for parameter discovery (CNN on Gaussian in PyTorch demo)

YouTube

Intro to PyTorch Tutorial: Building fashion recognizer

YouTube

Linear Regression using PyTorch C++ API (Libtorch) on CSV Files: Code Review and Demo Run!

YouTube

Demo - Face Recognition using pytorch (Arcface)

YouTube

An Overview of the PyTorch Mobile Demo Apps

YouTube
Return to navigation

Product Details

What is Pytorch?

Pytorch Technical Details

Operating SystemsUnspecified
Mobile ApplicationNo
Return to navigation

Comparisons

View all alternatives
Return to navigation

Reviews and Ratings

(14)

Community Insights

TrustRadius Insights are summaries of user sentiment data from TrustRadius reviews and, when necessary, 3rd-party data sources. Have feedback on this content? Let us know!

Easy to use: Users have consistently found PyTorch to be one of the easiest deep learning frameworks, with a simple model definition and easy hyperparameter setting. Many reviewers stated that they were able to quickly grasp the basics of PyTorch and start building their models without much difficulty.

Strong documentation and community support: The documentation and community around PyTorch are highly praised by users. Numerous reviewers have mentioned that they appreciate the comprehensive documentation provided, which has helped them troubleshoot issues and understand the framework better. Additionally, many users have reported quick resolution of their problems when seeking help from the active online community.

Versatile for research and development: PyTorch is considered an optimized and easy-to-use framework for beginners in the field of AI. It offers a wide range of data types and model architecture selections, making it suitable for both research experiments as well as production usage. Several reviewers specifically mentioned that they appreciate PyTorch's module writing style and seamless integration of various layers/architectures, which allows for versatile use cases in both research and development settings.

Inefficient Dataloaders: Some users have found that the dataloaders in PyTorch are inefficient and can cause bottlenecks in their training workflows.

Lack of Monitoring and Visualization Tools: PyTorch lacks good monitoring and visualization tools, unlike frameworks like TensorFlow which have tensorboard for visualization and creating plots during training. This has been a drawback for some users who rely on these tools for better insights into their models' performance.

Scalability Issues and Limited Platform Support: There are scalability issues with PyTorch, making it difficult to integrate into larger applications. Additionally, only a C++ API is provided, which makes deploying models on mobile platforms challenging. Some users have faced difficulties due to these limitations.

PyTorch is a highly recommended tool for beginners in the field of deep learning. It provides a user-friendly environment that makes it easy for newcomers to get started.

For experts in deep learning, PyTorch is also highly recommended. Its advanced features and flexibility make it a preferred choice among experienced users.

When comparing different deep learning libraries, many users highly recommend PyTorch. Its comprehensive ecosystem and support throughout the development process are valued by the community.

Depending on the specific use case, users suggest considering PyTorch or trying Keras as an alternative. This reflects an acknowledgment that different projects may have varying requirements and that exploring different frameworks can lead to better results based on individual needs.

Reviews

(1-5 of 5)
Companies can't remove reviews or game the system. Here's why
Taapas Agrawal | TrustRadius Reviewer
Score 9 out of 10
Vetted Review
Verified User
Incentivized
Pytorch is an awesome way of coding Deep Learning and Reinforcement Learning Algorithms with great ease. Since it is mostly pythonic, converting your derived equations/algorithms and using your favourite optimizers to test is so great. Further, it has great extensions to use like weights and biases where you can see how weights change in your neural network. It is an ideal tool for experimentation in Deep learning domain.
  • Provides Benchmark datasets to test your custom algorithm
  • Provides with a lot of pre-coded neural net components to use for your flow
  • Gives a framework to write really abstract code.
  • Since pythonic if developing an app with pytorch as backend the response can be substantially slow and support is less compares to TensorFlow
Pytorch is a great tool for experimentation and testing/developing ML flows and for reproducing results from top conferences. The components it provides with helps create Deep neural networks and flows with great ease and a level of cleaness.
  • The ability to use it to replicate historic algorithms
  • Derive and test new DL flows
  • It has a positive aspect as the ease of development results in publishing more papers for the community
Score 9 out of 10
Vetted Review
Verified User
Incentivized
We use Pytorch for Data Science related projects; it is a very advanced framework for doing Machine/Deep Learning for people who are already familiar with python. It has a lot of datasets and models integrated that can be used just with a few lines of code to create a quick POC. It's very easy to write our neural networks with Pytorch.
  • It's easy to write custom neural networks.
  • It optimises algebraic operation.
  • It has good support for computation on GPUs.
  • It should have support for Java also as Java is one of the most popular language.
  • They should make things more easy if we want to use GPUs for computation.
  • They should keep adding the latest models so that we can easily load them for use for further fine-tuning.
They have created Pytorch Lightening on top of Pytorch to make the life of Data Scientists easy so that they can use complex models they need with just a few lines of code, so it's becoming popular. As compared to TensorFlow(Keras), where we can create custom neural networks by just adding layers, it's slightly complicated in Pytorch.
  • Most popular datasets like mnist, etc are integrated.
  • Fine-tuning models is easy.
  • Community support is good.
  • It helped us creating quick POCs for customers.
  • We can do customisation as we need.
  • There is a learning curve so people need to spend some time for getting used to it.
Saving and loading Machine/Deep Learning models is very easy with Pytorch. It provides visualization capabilities when combined with Tensorboard, and mathematical operations are highly optimized. Easy to understand for a person who is an expert in Python. It takes significantly less time to create valuable POCs as most of the things are inbuilt.
Score 10 out of 10
Vetted Review
Verified User
Incentivized
We use Pytorch as the main framework for building ML models and writing data loaders. Being an AI company, we have to train a lot of deep learning models, which involves writing data loaders for our dataset, making networks, or using the existing networks from the torchvision library. Being an AI-first company, ML Scientists are supposed to experiment with the models, and that requires writing very robust and modular code.
  • Dataloaders
  • Deep Learning Models support
  • Excellent documentation
  • Excellent community
  • Support for major loss functions
  • Distributed data parallel still seems to be complicated
  • Support for easy deployment to servers
  • Torchvision to have support for latest models with pertained weights
Suitable for:
1. If you're working on some deep learning-related problem that requires some complex data loaders and augmentation strategies.
2. Gives you the support to use existing models and simply change the further layers, play with hyperparameters
3. Support for complex loss functions, optimisers, and schedulers which are required for handling complex training cases
4. Working on a big project that requires a lot of experimentation and model tweaking.

Not suitable for:
1. Playing around with simple ML models, use other libraries
2. Playing with small DL models with standard datasets like MNIST. Other libraries have very good support for them
  • Loss functions
  • Base dataloaders
  • Torchvision models
  • Neural Network module
  • Inbuilt optimisers, initialisers
  • Less time wasted on handling the library version issues
  • Small learning curve as very similar to Python
  • Compatibility with other popular Python libraries makes it easy to build a lot of things on it
Pytorch is very, very simple compared to TensorFlow. Simple to install, less dependency issues, and very small learning curve. TensorFlow is very much optimised for robust deployment but very complicated to train simple models and play around with the loss functions. It needs a lot of juggling around with the documentation. The research community also prefers PyTorch, so it becomes easy to find solutions to most of the problems.

Keras is very simple and good for learning ML / DL. But when going deep into research or building some product that requires a lot of tweaks and experimentation, Keras is not suitable for that. May be good for proving some hypotheses but not good for rigorous experimentation with complex models.
August 26, 2022

Pytorch in a nutshell

Score 10 out of 10
Vetted Review
Verified User
Incentivized
We are using Pytorch to construct computer vision Deep Learning models for a battery of projects in the Data Platform project pipeline. Pytorch delivers a very Pythonic way of dealing with Deep Learning models that, from our point of view, make it easier for us to put the code in production, work in teams and be able to improve those different models in an iterative way. The business problems that we are solving are the generation of models to predict different biomarkers in both 2D and 3D images to improve the selection of patients in clinical trials. Both the training and the prediction models in Pytorch are very friendly and with a lot of support from the community.
  • Training of Deep Learning Models
  • Generation of clean code that is explainable
  • Use of the last version of Nvidia images
  • Creating an environment to watch model training like Tensorboard
  • More pretrained models
  • More courses
Pytorch is very well suited to train Deep Learning Models in the Computer Vision field with the support of State of the Art models trained in that framework. There is a large number of pre-trained models and generated images to pick and start working. It can be less appropriate when the production part of the project is more important than the model itself; here, TensorFlow has some advantages.
  • Clean code
  • Dynamic Graphic memory
  • Pre generated docker images for cloud environments
  • The ability to make models as never before
  • Being able to control the bias of models was not done before the arrival of Pytorch in our company
As I described in previous statements, Pytorch is much better suited than TensorFlow from a software development look. This Pythonic idea was then taken and repeated by all the other frameworks.

You can get to better performance models by better understanding the deep learning model code, so I think the choice of Pytorch is easy and simple.
Score 9 out of 10
Vetted Review
Verified User
Incentivized
Pytorch is used to build ML models for recommender systems. As pytorch was developed in Meta it is frequently used across the whole organization (instagram, facebook, whatsapp, reality labs). We use it for quicker iteration, better debugging, and better support than some of its competitors. I can't talk about exact details too much for the products it's used for, but it is widely used in massive models that are put into production.
  • debugging is better than other frameworks
  • iteration is easy
  • pythonic syntax
  • great documentation
  • Would like more examples online of certain models
Pytorch is great for all deep learning models and is my go-to framework for this. It offers a great deal of flexibility which is a huge bonus when trying to get a new type of model to work or when you need to debug. The case where it isn't great right now is "on device" ML .
  • documentation
  • pythonic syntax and programming style
  • ease of use
  • I'd estimate I can build a model 50% faster on pytorch vs other frameworks
The syntax of PyTorch is much better in my opinion, and the programming style is more pythonic and easier to use. I also think PyTorch is a lot easier to debug than the competitors I've listed (Caffe2 and TensorFlow). I do like some of the examples given on tensorflows website, but PyTorch has good examples too.
Return to navigation