Thanks! I ran through the notebook and the fix was working. But the last line of the notebook fails
accuracy(pred,test_preds[0][1])
I did some tests and found that len(pred) is 3256 and len(test_preds[0][1]) is 1. So changed the code to check for
accuracy(pred,test_preds[0])
But the code is still failing with the following error:
Now I checked for the length of both pred and test_preds[0] and their types. Both match but still the above test fails.
Also I am not sure as to what we are comparing here and why. We have the accuracy and loss of each item of the test dataset for the 10 models. We get their average and then compare it against the first model accuracy and loss. Is my understanding correct? If so what is the intuition behind comparing this.
@muellerzr what channel can we view the recordings? Following it live from India would be a tad difficult due to the timings
We’re getting the accuracy on the average predictions of all 10 models, aka ensembling. The test_preds[0][1] may be a mistake, we want ground truths there to run our accuracy against.
@averma I’m unsure if I make a new channel for this or not but I will post the recordings here and in the top post when I do them 
As we are getting closer (one month exactly) I’ve decided that I will keep all the material in the Practical Deep Learning for Coders 2.0 repo and I will eventually rename it, as well as move over the lecture material once it is all there, as plenty of people have already starred it (thanks everyone who has! ) and are working out of it, as I do not wish confusion of “which repository do I use?”
Hi @muellerzr, I was trying the 04a_Rossmann notebook and came across the following error. Please help to debug.
Over the next few days I’ll be pulling the notebooks and putting up the new ones for the course. In the meantime I’d recommend these here: https://github.com/fastai/fastai2/tree/master/nbs/course
Also I will not be as active on the forums during the holiday season as I will be out of town. Any questions in those notebooks from that repository I’d recommend on the dedicated v2 forum by subject. I will be back a week before the study group begins. Happy holidays to everyone
Hi muellerzr Hope you are well!
Thanks for all the work and support you have given the community throughout the year.
If anyone deserves a holiday you do.
Have fun.
Cheers mrfabulous1 
I am comfortable in Java and have all the basic knowledge of programming. I understand the python code and have done a little python coding. I have taken part in one kaggle competition by applying the random forest code as shown in ML lesson 1
Awesome! Yep absolutely you’re more than welcome to join Welcome!
So as of now what shall I look into. I mean to say which course shall I look now before the meetup
I’d recommend the course v3 from last year to get familiar with how it all works. The API will change but they stay on the same concepts
The course v3 is about deep learning. Is it ok to skip the ML. I am confused with DL and ML. Is DL the next step after ML or both are different entities. One can start from DL?
I started out with DL as it’s all that the courses will be (the newer ones)
Awesome, can’t wait to join.
This is awesome news count me in!
Could you include some time series tabular discussion in the tabular section?
Happy New Year!!
Tom
Happy New Year everyone, we are just two weeks away! I’m very excited to do this with you all
Here is the YouTube channel everything will be uploaded to:
The plan is shortly after the streams have ended they will be posted.
On tabular:
I will do my best! The time-series library for v2 is currently not done, so I cannot dive into that. But I do have a few techniques (par if it winds up being post conference I plan on going to) I will present on. If not by that time, when I can I’ll make a notebook
Would love to see the revised notebook and results, comparing TabNet, Node, and Fastai.
