any chat for todays lesson not finding one any where
Lecture 2 is tomorrow! I also woke up early…Haha
You should save all the lectures from this google cal to yours and it will show you details of all lectures in IST.
Yes it’s tomorrow
A treasure!!
Do we get the link for lesson 2 as an email. I’m not able to find the link for tomorrow’s lecture.
You can watch the replay directly on YouTube. Only downside is you cannot actively ask questions during the session, but that is also what the forum is for.
Hi, is there any method to visualize the model architecture of ConvLearner or create_cnn objects.
Something like model.summary in Keras?
You should check tomorrow at forum before the lecture start time…there will be a Lesson 2 Topic and youtube live link there.
1 Like
got it. just printing learn or learn.summarygives the model architecture.
1 Like
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?
Training-Colab.png1210x209 18.8 KB
Here is another image I’m attaching
Train-1-Colab.png1212x175 18.9 KB
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?
Colab uses a K80. You can check using !nvidia-smi.
Run times correlate to the type of GPU used. Idk for sure about batch size. I suppose larger batch sizes mean less I/O and some sort of speed advantage, but maybe not. Batch size generally comes up in terms of fitting the data into the GPU’s memory, afaik.
2 Likes
I’m sorry if my question is trivial. I’m following the steps outlined in the notebook for multilabel prediction with planet Amazon dataset.
I have a trained model on one hand and unlabeled test data in a folder on the other hand. I would like to predict labels for all the unlabeled images. How do I go about predicting without having to loop through each and every image in the folder as in the single object prediction example?
hi,
I have this error installing fastai at work computer. Is there a way work around it?
error: Microsoft Visual C++ 14.0 is required. Get it with “Microsoft Visual C++ Build Tools”: http://landinghub.visualstudio.com/visual-cpp-build-tools
thanks!
1 Like
I’m trying to study the examples from Fastai github, but I get the same error every time:
Error: " Sorry, something went wrong. Reload?"
Please help!!
That seems to happen sometimes with github. Try nbviewer. As an example: http://nbviewer.jupyter.org/github/fastai/fastai/blob/master/examples/dogs_cats.ipynb
2 Likes
Hi Everyone, I have some black corners (because of transformation) in my training dataset images. Will this affect the prediction (Jeremy mentioned in 1st class to look out for any black borders or out of ordinary content in the image) if yes then how to handle this. Any help is appreciated. Thanks.
I would just go with your current data and see what is the accuracy. At least what I know it shouldn’t affect much if it is caused by rotation. I think Jeremy said that was because if all your images have huge black border before even transforming there could be something wrong with your implementation. And if there is some solution to get rid of those black boarder it could be nice to hear how much better it made the model.
Only easy way which I come up is to zoom in little bit so black isn’t showing anymore but I don’t think it will make any difference.
1 Like
Not sure why this happens, but it did happen to me this afternoon with another repo. For a temporary measure, you might want to use this webpage (http://nbviewer.jupyter.org/) to view .ipynb by coping URL into the specified field.
Hello! I don’t know do I writing to right topic.
I suppose that it is good to add class labels to that function:
fd = FileDeleter(file_paths=top_loss_paths).
Because as i mentioned due to hand data cleaning: some photos are from wrong classes.
For example, if asked for photos of angry person, there are also those photos which captions were: ‘not angry’ and so on. But my second class is happy persons, so I have some happy persons inside angry and can’t check this with FileDeleter.
1 Like
Please access it by cloning the repository and running jupyter notebook from your command line in the desired folder.
In this way, you can experiment with it as well (first create a copy).
1 Like