Unofficial release of part 1 v2

[init_27 (Sanyam Bhutani)]

We’re not being discouraged from starting the v2. We’ve been asked to wait to share it across social media until there’s a course website in place.

The course website will have all the resources related to a lecture linked, etc. so it’ll be easier to learn faster.

Nevertheless, the course is open to access, you’re welcome to start your journey.

[linmingwang]

Can’t wait to watch it. Thanks jeremy and happy new year!

[jeremy (Jeremy Howard)]

In this note, are you discouraging new folks from doing v2 “… until we’ve got a full new course website in place.”

Not at all! I would strong encourage you to use the new course.

[emsart]

@jeremy Thanks for posting the new material and presenting Paperspace. Happy New Year to you.

[reachtarunhere (Tarun Kumar)]

@jeremy Thanks a lot. At some point in the video, you mentioned the Practical ML course. I see notebooks for that in the fastai repo too. Any plans on when it will be released? Happy New Year!

[ecdrid]

The lectures links for the Machine Learning For Coders are available in the forums…
Here,

Another treat! Early access to Intro To Machine Learning videos

We’ll be releasing a new course (tentatively) called Machine Learning For Coders towards the end of the year. It’s being recorded with the masters students at MSAN. I’ve decided to share the videos with you all as well, since for those of you that haven’t done any ML before, you might find this a helpful additional resource. It uses the same fastai library as our deep learning course, so your existing repo and AWS instance will work fine. Here’s the videos - I’ll update this thread as they’re a…

It’s worth watching them…

[irshaduetian (Irshad Muhammad)]

@jeremy
I started the part 1 v1 ( http://wiki.fast.ai/index.php/Main_Page, 2016 version) of this course around two months ago, should I leave that course and start with this one, or I should complete that first then start this.

[Even (Even Oldridge)]

I started the part 1 v1 ( http://wiki.fast.ai/index.php/Main_Page, 2016 version) of this course around two months ago, should I leave that course and start with this one, or I should complete that first then start this.

As someone who has taken both versions I’d say it’s mainly a question of whether you’re more interested in Keras/tensorflow or in Pytorch.

The new version includes a lot of very powerful techniques that have been developed over the past year but they aren’t essential to learning deep learning and either course will provide the fundamentals.

My personal recommendation would be to look at both as they provide the same content in slightly different ways. I found that in order to really understand what was going on (and Jeremy recommends this as well) that it’s helpful to watch the videos multiple times, and one way to do this would be to look at both courses.

Either way there’s a lot of overlap in the material and you aren’t missing out on much by doing V1, especially if you follow up by taking a look at V2 and learning pytorch as you do.

Just my 2 cents.

[Manishankar]

Thanks a ton @jeremy … a couple of queries

1. is there a part 2 V2 to be expected?
2. I’m partly done with part 1 v1 and seriously considering building my own deep learning box as suggested in part 2(costs around INR 1,70,000 including GTX 1080 Ti 11GB ). I’ve been through some material that suggests waiting sometime before investing in hardware (http://timdettmers.com/2017/12/21/deep-learning-hardware-limbo/ ). would like your opinion on the same… even if the market changes to accommodate Nervana/AMD, is nvidia/CUDA likely to remain the standard for near future, say 12-18 months? or should one wait for better, affordable alternatives?

[irshaduetian (Irshad Muhammad)]

Thanks man for your answer, it really helps.

[ecdrid]

Yes for sure …
everyone is desperately waiting for Jeremy’s announcement for part2 V2…

[Kjeanclaude (Kouassi Konan Jean-Claude)]

Thank you @jeremy, I was waiting for that to have a deep knowkedge of your new pytorch based fast.ai deep learning library.

[jeremy (Jeremy Howard)]

is there a part 2 V2 to be expected?

Yes it’ll be taught in person from Mar 19, and online middle of the year.

I think getting a GTX1080ti is a good idea if you can afford it.

[Ray2 (Yihui Ray Ren)]

Happy new year!
Thanks a lot!
I will share this great news via social media.

[dol_re_mi (cmaster1324)]

Happy new year!
I will switch to V2 directly since I just finished lesson 2 in v1

[markovbling (alex)]

AW YISS!! so excited!

[MTAU]

oh wow. Not sure how I missed this announcement over the last couple of weeks.

Recently completed with the Brisbane cohort doing the course, we will likely be starting part 2 as a group in the next month.

Will there be an update of part 2 in the near future?

[jeremy (Jeremy Howard)]

Yes part 2 starts in person March 19. Will be online a couple of months after completion.

[ksasi (Sasikanth Kotti)]

Ths is great.Thanks for making these courses available.

[Seperthar (Seth Harper)]

Hi Jeremy, I am almost certainly more of a beginner than most to this topic. I am working on creating a server from home as I have a GeForce GTX 970 GPU.
I have installed Ubuntu to dual-boot with windows but I am struggling with the paperspace setup script. When I run the
"curl http://files.fast.ai/setup/paperspace | bash" command, it returns with
"rm: cannot remove ‘/etc/apt/apt.conf.d/.’: no such file or directory.

When I just run the script by pasting each line one by one, when I get to,
"sudo rm /etc/apt/apt.conf.d/."
the terminal just closes. Any idea of what could be going on or how to fix it? Thanks.