A walk with fastai2 - Vision - Study Group and Online Lectures Megathread

fastai
111

Hi muellerzr hope all is well and you are having a superb day!

Has the streaming URL been released for tonights lesson yet?
If so can you just confirm what it will be or what time it will be available.

I know the course starts at The livestreams will be from 5pm to 7:30pm Central Standard Time on Wednesdays.
For me this is normally bed time so I would like to check everything a few minutes before the stream starts.

Cheers mrfabuous1 :smiley::smiley: ps. nice video!

1 Like
112

Hi All!
To help @muellerzr with the SG, Iā€™ll volunteer to be an unofficial TA.
Please feel free to @ me for any/all questions-Iā€™ll be taking up the SG and even though I might not be able to provide as wise answers as Zach, Iā€™d be happy to make myself available.

Looking forward to being a part of the SG and walking the walk w everyone :smiley:

Best Regards,
Sanyam

10 Likes
113

What is the link to join the study group please?

1 Like
114

Youā€™re already here :slight_smile: if it gets too cluttered I may make separate threads for the topics (vision, tabular, NLP)

@mrfabulous1 I will post a link to where it should go live at here later today.

4 Likes
115

Note that we have a complete example of this here:

2 Likes
116

Thanks for the response! :slight_smile:

Iā€™ve gone through an older version of this notebook, but it doesnā€™t have exactly what I was asking here:


I was asking about Learner, which the notebook has an example of, but after following @muellerzrā€™s response, I realised what I actually wanted to construct was a cnn_learner. Hereā€™s how I did it:

arch  = torchvision.models.mobilenet_v2
mobilenet_split = lambda m: (m[0][0][10], m[1])

learn = cnn_learner(data, arch, pretrained=True, cut=-1,
                    split_on=mobilenet_split)

For future readers: cut was essential to make cnn_learner work, and mobilenet_split divides the model into 3 layer groups, allowing you to make use of different learning rates for different layer groups.

UPDATE: This is now part of the fastai library, courtesy of this PR, so you can simply do this in code:

learn = cnn_learner(data, models.mobilenet_v2, pretrained=True)
5 Likes
117

Here is the link for the stream:

(It will go live at 4:45 CST)

8 Likes
118

@muellerzr I suggest you put this in the top post too.

1 Like
119

Done! :slight_smile:

120

Thatā€™s because the default for the splitter param to Learner is trainable_params. Note that create_opt starts like this:

def create_opt(self):
    self.opt = self.opt_func(self.splitter(self.model), lr=self.lr)

So set splitter to any function that takes a model as a param, and returns a list of parameter tensors. That creates your layer groups! :slight_smile:

3 Likes
121

Slight tech delays on my end, the stream should be up by 5

122

We are live!

123

The words in the slides are blurred - canā€™t read them :frowning:

124

The video stream seems to be very choppy atleast for me

125

Yeah Iā€™m sorry for that guys, internet is very poor in this room right now :frowning:

126

No worries! Enjoying the presentation so far. Thanks for doing this!

127

Obvs just build a fastai hi-res & audio youtube fixer and re-release in 4k. :wink:

Donut worry about it, this is an awesome thing you are doing. Tech will sort itself out with time.

8 Likes
128

Hi muellerzr great lecture!

How would I go about solving the following problem. Is it currently possible?

I have image and I want to segment it on color.

So If I had a chess board image, it would produce two segments black and white.

Cheers mrfabulous1 :smiley::smiley:

129

Thanks guys for tuning in. Apologies for the tech issues, hopefully they will be sorted out next week :slight_smile:

1 Like
130

Iā€™d imagine thatā€™d be similar to CamVid and masks? :slight_smile: or are we talking coloring it in