Platform: Colab ✅

vikasmech · October 28, 2018, 5:48pm

ConvLearner vs Learner.create_cnn
In Collab ConvLearner works, instead of Learner.create_cnn. Fastai versioning issue?

tabshaikh · October 28, 2018, 6:00pm

Yes getting attribute not found error

jeremy · October 28, 2018, 6:14pm

If you conda update now that should be fixed.

maryam · October 29, 2018, 1:28pm

Previously, Convlearner worked perfectly on Colab, but now I get this error : name ‘ConvLearner’ is not defined. Is there any change in the library?

khengoon · October 29, 2018, 1:37pm

Please refer to this guide to setup Colab with the latest fastai library.

Fastai library was updated (i think yesterday) and Convlearner() is replaced with create_cnn().

jeremy · October 29, 2018, 1:47pm

Yes - please see the official updates topic:

maryam · October 30, 2018, 6:28am

I confronted a new problem in setting the colab. This code " !curl http://course-v3.fast.ai/setup/colab | bash "does not work anymore for me,and I get this error
bash: line 2: syntax error near unexpected token `<’

satyajittarai · October 30, 2018, 8:11am

Can you please screen shot. I think this syntax error. As this works for me.

satyajittarai · October 30, 2018, 8:11am

Can you please screen shot. I think this syntax error. As this works for me.

maryam · October 30, 2018, 9:12am

Thanks. I think I found the problem. It was due to using http instead of https.

Bhuvana_ka · October 30, 2018, 10:59am

Hi,
You can install fast ai with the following commands in Colab

!pip install torch_nightly -f https://download.pytorch.org/whl/nightly/cu92/torch_nightly.html
!pip install fastai

Neural-instinct · October 30, 2018, 6:19pm

Hi,
I want to know a better understanding of this animated training of ResNet34 model in Colab
1.What GPU does colab use?
2.What is that number 92 denote during the training?

Here is another image I’m attaching

1.Why does my losses are higher or varies significantly compared to the one that was shown on the tutorial?
2. Is training time an indication of GPU or batch size?

gamo · October 31, 2018, 4:31am

Colab uses a nvidia K80 gpu (you only get half of it though)
The number 92 is the number of training examples or batches in the training set, 74/92 tells you that it has process 74 of 92 batches.
Depending on how you initialize the model, and random seed, the databunch and learner will/can use different random numbers and give different results. Alternatively you have forgotten to run a cell in the notebook or there is something wrong with your code.
As far as a better GPU gives you faster processing time and the “right” batch size allows the GPU not to waste time loading partial data, yes to both.

amisha · October 31, 2018, 5:44am

!curl https://course-v3.fast.ai/setup/colab | bash
Will I have to run this command every time I start working on new jupyter notebook, if I am using Colab?

apparle · October 31, 2018, 9:34am

Is there a way to install jupyter notebook extensions in the colab environment ?

I’ve been using https://github.com/lambdalisue/jupyter-vim-binding when experimenting with local notebooks. Wondering if someone has figured out a way to enable this or any other notebook extension.

Memunati · October 31, 2018, 11:07am

i think so

gamo · October 31, 2018, 12:22pm

Yes, and everytime you reset your runtime.

You will also lose any data or files on the instance between sessions, so backing up your project data and models is necessary.

Memunati · October 31, 2018, 1:00pm

how do i back up my project data and models?

riteshc6 · October 31, 2018, 1:03pm

go to file -> save a copy in drive

Memunati · October 31, 2018, 1:04pm

Hello,
i don’t understand why it keeps getting interrupted. I’ve tried running it multiple times but it still the same.