I have question regarding the rossmann model.
Would it be possible, to change the model in a way, to predict sales for a new store, that has not been given in the training data? If so, how would one accomplish that.
Any help is more than welcome!
Hello everyone - I would like to post a question on the forum? Really sorry but I cannot see how to do this. Thanks in advance!
Hi @aruland1987, I don’t remember if you need at least few interactions in the forum, before you can post something.
In any case just try this:
- got to https://forums.fast.ai/c/part1-v3
- on the top right corner you see this button:
Ok, I think that’s all 
I have been watching the old “Intro to Machine Learning” course and have already finished the “Practical Deep Learning for Coders”, and I wanted to know if there is the concept of “Feature Importance” and “Partial Dependence” when using tabular learner as opposed to a Random Forest model.
How to create a new topic here. I was trying SGD from lesson 2 of part 1 and I am getting this error in loss.backward():
RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn
hi i have started Practical Deep Learning for Coders, v3 part 1 and i tried exact code as from github that was linked to the course video and i am facing error. I have gt1050 2gb graphics card and error code displays as CUDA out of memory is gpu is not sufficient or anyother problem am attaching the screenshot of that error code plz reply ASAP and hope to get reply from anyone …fast.ai lecture 1 image classification - Jupyter Notebook.pdf (115.8 KB)
HI Akhilessh hope all is well!
I don’t have a GPU but the the first two lessons do not need one.
I remember from the video that Jeremy has a 8gb or 11Gb card.
I would suggest reducing the batch size to 1, 2, 4 etc to see if this helps.
hopefully someone who owns their own GPU can help you further.
cheers mrfabulous1 
i have tried to reduce the batch size to 2 and i also have 8gb but i got the same result anyways thanks for the advice hope to solve the issue ASAP Thanks for response@mrfabulos1
1 Like
i have solved the issue in the batch size i have reduced it from 64 to 16 and it worked so if any facing any issue regarding the cuda has no memory try to change bs=16 if u have low memory
Can someone tell me how to post questions as in make new post? I’m guessing that it is disabled till I make some replies or something like that.
Coming to the actual question, I had some issues with Mixed Precision Training. Everything seems to work fine, though the speed gains are marginal, I can effectively double the batch size. I’m having problems on selecting a good learning rate using the lr_finder. Am using suggested value using suggesation=True but it overfits by a huge margin, taking multiplying the value with 0.01 seems to be doing good it just overfits a bit but it’s more or less guess and check. What is the correct way to choose lr when training with mixed precision
I’m working on ImageNet data, 80/20 test/validation split using 4 GTX 2080ti with a size=224 and batch size=512 using SGD. fastai version 1.0.60dev and pytorch verion=1.3.0. Below are the pics for lr divided by 100
Hi
Regarding lesson 5 (Movie rating): the loss function is set to RMSE between an int (the rating), and a float (network result). Is it possible to add a round mechanism at the end of the network? or alternatively define an activation function that looks like stairs (continuous input, semi discrete output)?
Thanks,
Ohad
I’ve just started this course and am going through lesson one. I’m noticing some inconsistencies, for example, in the training resnet34 section my notebook has “create_cnn” as the code but the video shows “ConvLearner”. I also have a “learn.model” piece of code in my notebook but the video doesn’t show that.
I’m a complete beginner, so pardon my ignorance, but why is the notebook different from the video?
Hi https://forums.fast.ai/u/learningML89 hope your day is going well!
The videos are older than your current version of fastai, if you are using v3. Use the video as your guide but stick with the code in your notebooks as this is the most current and definitely works.
Cheers mrfabulous1 
1 Like
@jeremy
How do i get started with fast.ai deep learning course from zero to hero ??
I know some deep learning courses, i have some experience on deep learning but not all, I have knowledge on programming and python. Except certificate i dont have any on github projects .
How do i get into this fast.ai deep learning course step by step from Zero to Hero to capstone project on github ?
Thanks for the course for free for humanity,I am Hoping to make something benifit for our humans,
Hey , how to set the Oxford 102 Flowers Dataset DataBunch . I just started the course so i’m new to this.
I have a question regarding lesson 2.
When grabbing URLs for photos in our dataset, do we have to use the “url_class.txt” format or can we just name it “class.txt”? If not, why?
Hi,
I have been trying to work on the camvid data set of lesson 2, but I wanted to change the dataset to only have 11 classes not 32 does any one know how this can be done.
Thanks,
Aly
1 Like
I’m working on the camvid notebook for lesson 3, and would like to try segmentation with another dataset. Up to this point, I’ve only used the method in lesson 2 with google images.
I see in the notebook, it’s looking for URLs.CAMVID. Where is that stored in the notebook, and if I were to download another dataset, is there a tutorial for how to upload it so I can access that in the same way?
URLs. CAMVID is just the variable for a link to a download for the CamVid data set. Untar_data just fetches the file and then untar’s it locally so you can access the data.
If you want to try things out on a different dataset you will need to download a dataset to your practice environment and then use the same methods he uses to put the data into a DataBunch and add the masks.
I just did a quick search but here is a list of other image segmentation datasets, although they all appear to be the same type of data as the CamVid stuff.
(https://blog.playment.io/self-driving-car-datasets-semantic-segmentation/)
1 Like
It is not a course with a capstone… You learn what they teach and try to apply it to an area you already know a lot about. You should then spread the news in your industry. Or you practice a lot of past kaggle competitions.
1 Like