Nope. Maybe @radek ??
I have ordinary PC box, not a headless. But make notes on your struggle, would be great blogpost.
Have not experienced any issues - went for EVGA FTW3 because of its cooling.
Different GPUs will have different heat characteristics - for instance, a ZOTAC mini will nearly instantly heat up to ~90C.
I would not worry too much about fan control, etc unless you are seeing genuine issues (restarts, etc)
Issueas are the main reason I worry about fan control and I think that fan doesnāt work on max speed when it should 
maybe this article will help you:
you have access to nvidia-smi? It should show you GPU-fan usage
Iāve already read this blog post (just minutes ago) 
Iāll try that scripts this evening. Thx for help. Wish me luckā¦
You can get GCP with regular card (debit card) no credit card required. Iāve got up to watch the lecture and was half-awake most of the time, eeh.
When I run learn.unfreeze() it unfeezes all the layers from what I understand, but it doesnāt learn from scratch just adjusts the existing weights? Because when I do unfreeze, learn, save, weights and load them and then run the sequence again I have different error rate.
this is what i understand too. that is unfreezing doesnāt āresetā pretrained weights (for this there is pretrained=False argument).
when you load weights and run more epochs, the error decreases? i think it should unless it overfits?
Yes it decreases, I think I will experiment more on dataset that is processed faster (I did that on quick draw, using Radek tutorial, thanks for that Radek).
@Blanche @Michal_w @sayko
was good meetup! thanks for joining today! however there was a huge echo on my side i could barely hear you today. i hope next week will be better!
3 Likes
maybe interesting for GCP users, additional $500 credit: https://forums.fast.ai/t/platform-gcp/27375/140
5 Likes
if someone is training of colab there is a easy way to use own dataset, if it is on Google Drive.
2 Likes
@sayko @Blanche @Michal_w @tillia @piotr.czapla @radek @Gaurav85 @Emsi @wojtekcz
our hangout video call is today at 20.00. see you all there! join us using this link
3 Likes
Anyone has link to Video Stream of lesson 3 ?
Michal
are you watching live?
@miwojc
https://forums.fast.ai/t/new-guide-for-easy-web-app-deployment/29616/2
I saw you asking about situation, where there are not only cats/dogs (example) but also not-cats-dogs, other category.
https://blogs.technet.microsoft.com/machinelearning/2018/05/01/how-to-develop-a-currency-detection-model-using-azure-machine-learning/
Here is example:
They added additional category ābackgroundā and made it 5 times bigger then other categories.
āThe backgrounds should be as diverse a set as possible.ā
1 Like
If someone wants to get into Reinforcement Learning (I do 
) , OpenAI just launched https://spinningup.openai.com/ . It looks like a great resource.
3 Likes
nice. thanks @sayko !
jeremy just tweeted yesterday that someone beat fastai teamās DAWNBench CIFAR10 training record by factor of 2.5x, interesting read:
1 Like
Thanks for sharing !!! Otherwise I would missed this and the article explains a lot !
1 Like