Welcome to forums.fast.ai

How can I create a new topics to ask questions?


did you come around to the datablocks api?

You have to have a certain reputation level. (Few likes, few comments) if you have tech problems ask the admins

1 Like

You need to wait for a short period of time.

Ok, just let me create a post to ask my question

1 Like

stumbled on the categories page that has a New Topic button, top right. hope that helps someone :slight_smile:

Just joined the fast ai MOOC Beginner course

Welcome. If you have any problem on the course, please feel free to post it.

If it is in colab, please post the notebook with a shared link, so people can work on your notebook to see the problem.

I am working on an image classification dataset{lions vs tigers} with the help of lesson2-download.py


Dataset is properly balanced with 199 images each.


After executing the learner, the results are like this
epoch train_loss valid_loss error_rate time
0 1.062792 0.040511 0.025316 00:04
1 0.579201 0.014106 0.012658 00:03
2 0.424722 0.005917 0.000000 00:03
3 0.330072 0.005360 0.000000 00:03

As we can see error_rate went to zero which I think doesn’t make sense(Overfitting ?? don’t know)
Adding to this learn.recorder.plot() gives empty graph.
As we can see from confusion matrix every image was properly classified(dataset is too easy for model ???)
Can anyone help me with this??

Thanks JonathanSum!!

I guess it is too easy for the model. You should download few image from google outside of your dataset and try it after using learn.export.

Suggestion, I see sea lion is also under lion section. If you make your data in, sea lion, lion, tiger, cat, you may not be able to achieve 100%.

ya, right… Thanks for the suggestion. Will try that
But do you have any idea why learn.recorder.plot() didn’t show any graph??

I am not sure. But I suggest try to start form a lower learning rate to a higher learning rate for “recorder.plot()”. Or you should just use recorder.plot().

Your problem is too easy. Two of the categories for imagenet are lion and tiger, so the pretrained weights have been extensively trained to recognize lions and tigers. There is also the possibility that the exact images you are using to train with are in imagenet.


I dont see any area where I can post about multi class classifier, I saw multi label but not multi class classifiers

I suggest you post it on Part 1 2019 section rather on this welcome section.

As you can see, it will classify more than one object in the satellite image. For more detail, you should read the doc.

Try using kaggle or Google Colab, which are both by google. I believe kaggle has gives 30 hrs of TPU and GPU, and Colab has unlimited GPU, but no TPU.

Hello,I am new to time series classification and I want to apply this developed software :
https://github.com/fastai/fastai2. One question I had after testing the code, is whether is possible to do multivariate time series classification using this code, cuz here they used the univariate data. If so, how could I formulate the data into pandas DataFrame to put it as df_train?

Gradient also has some free virtual machines and you’re able to hop into it pretty quickly. I’m unsure how they compare in speed to other options as I’m just starting this course, but I imagine it will get the job done. You can see other options here ‘https://course.fast.ai/’ under ‘Server setup’.

Hi Kaiyun. I suggest you post it in the 2019 lesson 1 section of the forum. In addition, the Rossman dataset video and its previous videos have talked it using a simple linear model. Moreover, if you can, please show us the dataset so people can help you with panda.