Hi, I am Conwyn from the UK. My future son in law is doing a PhD in DL so I asked him to explain it. He said it was difficult to explain so here I am. I have been coding since I was 12 although Python and Jupyter are new to me. I tried to run Jupiter on my laptop but it was too slow so I am using CoLab. I keep costing up building my own PC but I think I will stick with CoLab initially. I watched a video on OpenCL and wrote a quick test program with my laptop AMD GPU and it was 64 times faster than my CPU for exp(log(x)) for 400 million rows which brought the point home why we use a GPU. I have watched the first seven videos and I am now re-watching and running the notebooks. I find I have to break the videos into 30 minutes slots to keep my concentration. I am sure it has been said before but the trick is not to wander and put the 1000 questions on the list rather than trying to research them. I hope to complete everything before part II comes out in June.
Joseph Anuff from Vallejo CA, wanting first off to thank everyone for being such an inspiring student body. Obviously, Jeremy and Rachel and their developers deserve all conceivable props for making DL accessible and comprehensible—I’d already rate fast.ai the most format-validating MOOC ever, and they’re clearly just getting started—but this is still really challenging stuff. The sheer breadth of material seems to find the beginner in all of us. But seeing so many intellectually-accomplished people willing to be confused (and/or humanely instructive) in public gives a privately confused person like myself a lot of hope!
My background is in Web 1.0, Web 2.0, and TV production, usually in a producer role and mostly in the ‘90s and ‘00s. The ‘10s have been drastically less public or prolific, as I’ve pursued a more hands-on technical mastery of various layers in the media stack. For the last five years or so that’s taken the form of full-stack JS experimentation, sometimes for clients but self-directed, as much as possible.
By the time v3 dropped this year, I’d already binged on every fast.ai lecture (minus the last 5 Linear Algebra videos) and was about to start my second pass. (Since discovering fast.ai late last summer, I’d also consumed other common course-loads, biggest impacts being Andrew Ng, Data Camp, and Khan Academy. In years past, I’ve also taken EdX courses in Data Science with R.)
Over the last six weeks I’ve listened to each lecture five times: twice at 1.5-2x speed for familiarity, once with @hiromi’s excellent notes, once running the iPython notebooks, and once taking notes by hand myself. I tried maybe 5 of the server platforms, mostly successfully, before semi-settling on GCP. I assembled and trained an itchy plant classifier, but didn’t use it for my Render.com deployment because seeing some similar prior student projects put mine in turnaround. I’ve read all the lesson threads (in-class and advanced) at least once.
And after all of that, is Pt. 1 crystal clear? Well, I’d probably choke on a pop quiz, and that part where Jeremy recommends we be able to rebuild notebooks from scratch is not yet mission accomplished. But I’ll be damned if “The Matrix Calculus You Need For Deep Learning” isn’t starting to make perfect sense—where a month ago it honestly made me nauseous. And I’ll say this: by the fifth playback, Lesson 7 stood out as easily the most action-packed, idea-provoking lecture I’d ever heard.
Just looking at the subjects in the “Coming Up: Pt. 2” slide, or Jeremy’s more recent notes at fast.ai, gives me a classic Christmas morning rush. I can’t wait! Looking forward to meeting some of you in person, and all of you here in the forums.
Hi fast.ai community!
Im am happy and excited to join you. My name is Anders and I love programming, maps, web, open data, music and much more.
Can someone give me a bit of guidance? I cant post a new topic and cant find a suitable existing one for my error in lesson 2:
NameError: name 'cnn_learner' is not defined
Edit: nevermind - just needed to gain some basic trust from the system (browse some treads and do some searches, introduce myself here did the trick)
Your fastai library is not the newest version, try
create_cnn and it should work.
Thanks Hanz! It seems the excercise still works with
cnn_learner after my update. In the source code
cnn_learneris still referenced like that, is there a reason for that?
cnn_learner is the latest version of calling CNN learner, if it works then you are good.
I’m Akshay, a software developer at a YC startup based out of Vegas, currently interested in AI research, python developer.
It was wonderful to see you have started to do something with Swahili language. I am really inspired. I just wanted to know how far with the translation of the subset of MS-COCO dataset to Swahili.
I am new to fastai and Deep learning. I am interested in NLP and Computer vision projects.
Hello everyone, Vincent here from Kenya. Excited to be part of this community just finished lesson 1, and trained an image classifier on a dataset of plant diseases… Thank you fast ai team for this opportunity.
Hi Alex, nice to meet you, and thank you! I built this website: https://cocohub.cc to crowdsource translations of MS-COCO to African languages. Please join in and help contribute!
Hello World! My name is Michael and I’m in Chicago. Currently I’m a Data Analyst. I have been working with SQL for 4 years, Python for 2 and been learning data science for the past year and a half. Not exactly sure if the 2019 Course is “over” or if anyone can jump in at anytime, but glad to be here. If there is anyone in the Chicago area who wants to start up a study group let me know.
I’m Vineet, currently a backend developer trying to get more involved in Deep Learning to solve some interesting problems!
I am Gary from Hong Kong, I have been working as a mobile developer for almost 10 years, I just taught myself backend development and want to become a machine learning engineer, I hope this course will help me to start my journey.
i am Tahir. I am finding it impossible to use the notebooks using the exact commands from gcp tutorial page. such a shame.
Hello everyone. I’m excited to learn and very motivated to make a transition in my career to machine learning. I am hoping to gain as much from the course as possible.
Hi Everyone! I am Jasmeet from Canada - iOS developer who loves Machine Learning. I am interested in applying deep learning in real time surveillance data in order to reduce the crime.
I am also about to start my Masters in AI. So far, I am loving the fast ai course. Would love to contribute to it . @jeremy thanks for the course.
I’m Gopi, an embedded software developer majorly working with C. I am a newbie to AI domain. Landed on fast.ai course from my online research on AI and relevant courses. Really liked the top-down approach and starting my learning curve on AI here with fast.ai.
Looking forward to be active in the discussions here.
Kaggle kernels might be another option - free GPU, etc.
My name is Aditya and I’m super excited to do this course. I have a basic understanding of python and working on Jupyter Notebooks already. I am based in New Delhi, India. Would love to form a study group of sorts if anyone is interested. I’m a final year CS student.