My feelings on Part 1: I felt like the setup of the first part was at time a little frustrating, since I started it during a time when Keras had switched to a newer version which wasn't compatible some of the utility code that was written. Add this to the newbie factor to notebooks, and it was a pretty rough first week or so to setup and get actual learning done. It took me a bit of time to realize notebooks were mor…
Deep Learning for Coders – Launching Deep Learning Part 2
41–50 of 94 posts
Re: Deep Learning for Coders – Launching Deep Learning Part 2
#42My feelings on Part 1: I felt like the setup of the first part was at time a little frustrating, since I started it during a time when Keras had switched to a newer version which wasn't compatible some of the utility code that was written. Add this to the newbie factor to notebooks, and it was a pretty rough first week or so to setup and get actual learning done. It took me a bit of time to realize notebooks were mor…
Re: Deep Learning for Coders – Launching Deep Learning Part 2
#43My feelings on Part 1: I felt like the setup of the first part was at time a little frustrating, since I started it during a time when Keras had switched to a newer version which wasn't compatible some of the utility code that was written. Add this to the newbie factor to notebooks, and it was a pretty rough first week or so to setup and get actual learning done. It took me a bit of time to realize notebooks were mor…
Re: Deep Learning for Coders – Launching Deep Learning Part 2
#44My feelings on Part 1: I felt like the setup of the first part was at time a little frustrating, since I started it during a time when Keras had switched to a newer version which wasn't compatible some of the utility code that was written. Add this to the newbie factor to notebooks, and it was a pretty rough first week or so to setup and get actual learning done. It took me a bit of time to realize notebooks were mor…
FWIW, I think the supplementary material wasn't strictly necessary from a 'using the libraries' point of view. I'll never contribute to this field, but I feeling like Jeremy's explanation were conceptually helpful if not rigorous.
For me, the order was: lesson, notebook+lesson, wiki + supplementary material if something wasn't making sense, and the discussion board if all else failed. That discussion board is basically useless unless you're taking the class in real time I think, which has been my experience for all MOOCs.
Different strokes for different folks.
Re: Deep Learning for Coders – Launching Deep Learning Part 2
#45Earlier quoted context omitted.
If you have the hardware, you can do without an AWS account (you might need to be an "expert" to interpret the instructions to run on your own hardware instead of AWS). I used my gaming rig with a 1080 GTX Ti card.
Why? Why can't I just do it with my crappy hardware, and it take longer?
Re: Deep Learning for Coders – Launching Deep Learning Part 2
#46Re: Deep Learning for Coders – Launching Deep Learning Part 2
#47I'll go edit the post with this info now - but figured I'd add a comment here for those that have already read it.
Re: Deep Learning for Coders – Launching Deep Learning Part 2
#48My feelings on Part 1: I felt like the setup of the first part was at time a little frustrating, since I started it during a time when Keras had switched to a newer version which wasn't compatible some of the utility code that was written. Add this to the newbie factor to notebooks, and it was a pretty rough first week or so to setup and get actual learning done. It took me a bit of time to realize notebooks were mor…
CS231n is great and I'm glad you checked it out. There isn't really anything nearly as good online unfortunately for the other areas we covered (NLP, collaborative filtering, etc). CS231n is not as code-oriented as the fast.ai course, and doesn't try to get you to the point you can replicate state of the art results - but it's got great conceptual content and Karpathy is a terrific technical communicator. I think the two courses go hand in hand quite nicely!
Re: Deep Learning for Coders – Launching Deep Learning Part 2
#49Earlier quoted context omitted.
Apparently they're getting rid of annotations.
Ok then cards or whatever annotations have been replaced by, but something! https://creatoracademy.youtube.com/page/lesson/cards
When we redo part 1 in October, we'll try to find a way to incorporate a clear link to an errata page or FAQ in each video, so that anyone with issues has one place to go.
Re: Deep Learning for Coders – Launching Deep Learning Part 2
#50They don't even have a link to part 1 at the start of the article??
I'll also link the text 'part 1' in that paragraph to make it more clear.