Show HN: Deep Learning in TensorFlow – The Roadmap for Study and Learning
1–10 of 21 posts
Re: Show HN: Deep Learning in TensorFlow – The Roadmap for Study and Learning
#2This guide will be useful.
Re: Show HN: Deep Learning in TensorFlow – The Roadmap for Study and Learning
#3Not disparaging the author, good on you for working on building this! I’m sure you learned a lot from just compiling everything together.
My question is, isn’t everything in this guide pretty much just a straight up copy of the actual TensorFlow docs/guides? What’s the difference?
Re: Show HN: Deep Learning in TensorFlow – The Roadmap for Study and Learning
#4Thanks for the list.
Re: Show HN: Deep Learning in TensorFlow – The Roadmap for Study and Learning
#5It would be great to have some sort of roadmap depending on "what" the user is trying to do.
i.e. if I was a total noob and I wanted to make an application using AI to detect if people in the crowd were bored, I would have no idea where to start without reading/researching for hours online on different fields and models that work and how they work. It would be neat if there was a tool that just asked you a few questions, then took that info and gave you a roadmap, i.e. "Feed Forward Neural Networks, Digit Classification, Image Classification w/ Inception, Object Detection with ResNet + Inception, Optimizing TensorFlow code for Servers, Deploying TensorFlow with Docker, Protecting Against Adversarial Input"
This way someone with a time sensitive project doesn't have to learn TF for 6 months before being able to accomplish what they wanted! Just something I think would be neat and also possible to add to TF World.
Re: Show HN: Deep Learning in TensorFlow – The Roadmap for Study and Learning
#6Some well considered advice: drop TensorFlow and go with PyTorch. Spend your effort where it will make a difference: on deep learning, rather than on fighting with the framework.
People just keep using TF because it was the first full-fledged Python framework for this, not because it has any technical merit anymore. In PyTorch you will make twice as much progress in half the time.
Re: Show HN: Deep Learning in TensorFlow – The Roadmap for Study and Learning
#7It would be great to have some sort of roadmap depending on "what" the user is trying to do. i.e. if I was a total noob and I wanted to make an application using AI to detect if people in the crowd were bored, I would have no idea where to start without reading/researching for hours online on different fields and models that work and how they work. It would be neat if there was a tool that just asked you a few questi…
+1 for this one!
Re: Show HN: Deep Learning in TensorFlow – The Roadmap for Study and Learning
#8Some well considered advice: drop TensorFlow and go with PyTorch. Spend your effort where it will make a difference: on deep learning, rather than on fighting with the framework. People just keep using TF because it was the first full-fledged Python framework for this, not because it has any technical merit anymore. In PyTorch you will make twice as much progress in half the time.
Is there any way to use a pytorch model in Mobile and in a website without a server API? For me 5hose are two good reasons to keep using TensorFlow.
Re: Show HN: Deep Learning in TensorFlow – The Roadmap for Study and Learning
#9It would be great to have some sort of roadmap depending on "what" the user is trying to do. i.e. if I was a total noob and I wanted to make an application using AI to detect if people in the crowd were bored, I would have no idea where to start without reading/researching for hours online on different fields and models that work and how they work. It would be neat if there was a tool that just asked you a few questi…
There are not so many type of problems for such a complex tool. Your problem usually fits in one category among classification, prediction, clustering, generation or control. Then you have different domains as images, video, audio, text, etc. With a combination or type of problem and domain you sure can have a roadmap, but you probably will need to read papers to solve your problem if it is not something some has done before.
Re: Show HN: Deep Learning in TensorFlow – The Roadmap for Study and Learning
#10Some well considered advice: drop TensorFlow and go with PyTorch. Spend your effort where it will make a difference: on deep learning, rather than on fighting with the framework. People just keep using TF because it was the first full-fledged Python framework for this, not because it has any technical merit anymore. In PyTorch you will make twice as much progress in half the time.
Is there any way to use a pytorch model in Mobile and in a website without a server API? For me 5hose are two good reasons to keep using TensorFlow.
https://caffe2.ai/docs/AI-Camera-demo-android.html?
Not something I've used myself, but supposedly yes.