Thank you @jeremy,
For my installation on the Windows 10 I have been limited by pytorch which does not run on Windows (even if tensorflow and keras work well on through Anaconda 3). This is the reason why I used a VM.
For the Ubuntu bash from the Wiki, as it was designed for python 2.7, I have adapted it to python 3 using the setup info you gave on the setup thread.
So all run well on my VM.
I have also tried a shared Docker on Windows, and it work on, I will propose a post on later as my contribution to the Wiki.
+1 if you are not using direct hardware support (like GPU), Ubuntu Bash for Windows is fantastic and is the best option for Windows. It’s is pure linux binaries, not emulated. You just can’t do anything that uses direct access to hardware like GPU or Network card.
In an earlier message on this thread I asked everyone to add their name and timezone. If you add it now, we can create a group for people that missed the last request.
Done. Sorry, I overlooked this earlier post.
re: study project: I am in the kaggle DSB and the fisheries one. Other than that anything crazy or creative would do.
Perhaps building a cool web app for style transfer? A beatbox companion based on wavenet? Right on.
As a biologist, I also would be happy to work on a biological / biomedical data set.
Hi ! Ubuntu Bash for Windows : Do you talk about another bash different from those of this link (in the wiki) ? : http://wiki.fast.ai/index.php/Ubuntu_installation
If it is the case, please give me the link, I didn’t find any info about from the wiki search link.
Here you go, this only works in Windows 10 and will not allow you to use software that requires hardware level access (like Tensorflow-GPU, network scanners and so on. Tensorflow and PyTorch without GPU support work good though.
Ok, I remember they announced that last year as in development (as an insider I test some builds when I have time). But I was not aware that it was already out.
I will try anyway and give a feedback.
Thanks.
Can we learn how to balance binary trees in the next lesson? Apparently it’s now a requirement to enter or leave the country.
Balancing a binary tree is way of storing data. Most programmers use them, but few programmers ever need to create or balance their own. “I’ve been programming for over 30 years and am much more involved in the algorithmic details than the vast majority of programmers,” says Jeremy Howard, an Australian programmer and entrepreneur who has founded multiple startups and teaches an online course on artificial intelligence. “And I’ve never actually needed to balance a binary tree.”
Hey all, can anyone share the streaming links/instructions used to attend Jeremy’s lectures? I’m going to be away next Monday but would still love to attend class. Thanks.
Hi @shgidi,
I also have a personal project too for audio video translation (too heavy to start on now I think) but we could discuss later … More details here on my github : https://github.com/Kjeanclaude/Verbos
For your idea, I have already read several papers about clustering in videos.
I am in the GMT+0 timezone and I would be glad to discuss and work with you.
Please join the spreadsheet above (This one), and add your input, with the agreement of Jeremy she should be on the same team.
Hi @shgidi,
Here are some papers about clustering in videos/images (most of those I read are from arXiv):
I add some in relation with what we have already learned in this course (style transfer), but applied to videos.
I missed the 2nd part of the last session. I thought, we can watch the recoreded live streams directly after the class. When I open the link, I don’t see any recoreded videos. Any ideas?