1. Home
  2. Machine Learning Tools
  3. Pytorch Reviews
  4. User Review of Pytorch
Pytorch: Best framework for building AI models
August 26, 2022

Pytorch: Best framework for building AI models

Anonymous | TrustRadius Reviewer
Score 10 out of 10
Vetted Review
Verified User

Overall Satisfaction with Pytorch

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
  • 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.

Do you think Pytorch delivers good value for the price?

Yes

Are you happy with Pytorch's feature set?

Yes

Did Pytorch live up to sales and marketing promises?

Yes

Did implementation of Pytorch go as expected?

Yes

Would you buy Pytorch again?

Yes

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