General course chat

(Francisco Ingham) #56

I am sorry about the confusion. Could you try this guide instead with Python 3.6?

I think it should work but let me know if it doesn’t.

(hector) #57

@areevesman I think this is the correct thread to get this adressed


Wasn’t sure where to mention this but

Step 4: the file dir seems to have changed and this:

cd tutorials/fastai/course-v3
git checkout .
git pull

…no longer works and as such is obv no longer a git repo.

Would be good to get a steer also on where I should mention these corrections going forward if this is wrong place :smile:

(Jeremy Howard (Admin)) #60

Yup fixed that earlier today - thanks. Better places to mention are , or best is a PR to


I am trying to run the pets-notebook and I encounter the following error:

----> 1 learn = ConvLearner(data, models.resnet34, metrics=error_rate) AttributeError: module '' has no attribute 'resnet34'

Any ideas?


This error is speficially mentioned in the FAQ. Don’t forget to check it, or do a quick search on the forum before posting!


Any chance you might include a lesson on Text to Speech? I find Deep Voice 3 fascinating

I’ve been try out a couple of open source implementations which work pretty, it would be nice to understand more about how they work…

(Jeremy Howard (Admin)) #64

Yes I’d like to in part 2.

(Theodoros Galanos) #65

FAIR released faster R-CNN and Mask R-CNN for pytorch 1.0, if anyone is interested. Good place to take a look until we go over it in the course (I’d guess part 2).

(George Zhang) #66

Try to look and see if there is a course-v3 folder under under the home directory with ls.


understood - thanks for clarification.

(Jeetendra Kumar Sharma) #68

Just wanted to understand whether building out following capability possible via fastai library. i know after going through the v3 docs that it has support for image and video but still little bit confused as to how to approach the solution. Following is the link.

Any help in this regard would be appreciated.

(David Pfahler) #69

Are we going to see sequence labeling in this course or any other NLP related tasks?

(Iwashokun Opeoluwa) #70

I am currently in Nigeria and the local time of tge course for me is weekdays @ 2:30am. Its really tough to stick around. Can anything be done as regards it.

(David Pfahler) #71

Same for me. Unfortunately, someone around the globe has to bite the bullet. If it is too disruptive for you, you can always rewatch the YouTube stream the following day.

(Iwashokun Opeoluwa) #72

Ok thanks for the reply. I am watching d video of the first class. I am finding it difficult to join a study team - cant seem to find any on my timezone. Pls can you help with suggestions also?

(Benoit) #73

Africa+1 is in the same timezone as Europe+1 so if you find nobody in Africa (it will suprise me) you could join a European group.

(Iwashokun Opeoluwa) #74

Thanks Benoit. I found “Lagos study group”

(Carlos Vouking) #75

Hey Opsy, try to make the effort staying awake. Trust me it’s a great moment. It’s just once a week. And if you can’t, the recorded video is available right away.


(Daniele Galiffa) #76

I’m also interested