alirezadir/production-level-deep-learning

A guideline for building practical production-level deep learning systems to be deployed in real world applications.

production-level-deep-learning's Issues

Suggest adding Diffgram

Under labeling platforms, ie L37 on readme, ie:
* [Diffgram](https://diffgram.com/): Computer Vision, Training Data

Suggestion regarding tools and platforms

Hi @alirezadir. Firstly, thank you very much for putting this together. Really awesome! In this issue, I would like to take the opportunity of suggesting a few tools/platforms with which I have worked and I believe it could be beneficial:

• For Data Storage, Google Cloud Storage.
• For Data Versioning, FloydHub Datasets.
• For Data Processing, GCP Dataflow.
• Under the Software engineering for Cloud Providers, you could also mention the specific services offered by the cloud providers. For example, Compute Engine and Notebooks (GCP Notebooks does not require any configuration and can increase the productivity) for GCP, EC2 for AWS and so on.
• You could mention ML Engine which eases out the process of distributed training (under Distributed Training section).
• For the Troubleshooting section, this Twitter thread by Chip could be very useful.
• For the Web Development section (and for general model serving purpose), BentoML could be useful.
• For Monitoring, Stackdriver could be useful.

Thank you for reading!

why cpu better ?