Lesson 3 - Official Topic

If you do need to deploy directly on a phone, you can use PyTorch Mobile as well.

3 Likes

Yes, this is not easy and it’s the drawback with Classification in DL today. Hence my question.

1 Like

I don’t think you have to train a model to recognize “not-bearness”. You have to train a model to find features that indicate “bearness” and in the absence of “bearness” it would output “not bear”.

For example I can train a model to recognize my face. I don’t have to give it the face of all other people on earth in order to train it.

3 Likes

Maybe to see how not sure the model is for a given image say and setting a threshold? Would that approach work?

is Caffe2 another way of deploying PyTorch models like ONNX ?

2 posts were merged into an existing topic: Lesson 3 - Non-beginner discussion

Look into this maybe?:

3 Likes

You are talking about binary classification. Sure works and we all know that. Multi label classification is where issue is.

As we will see later on, it won’t work with this model which has to produce numbers that add up to one. You need another kinds of model/loss function for this. Stay tune for the lesson about multi-labels problems :wink:

2 Likes

I used that approach to offer a ‘second guess’ classification if the % was below a threshold
https://sportsidentifier.azurewebsites.net/

1 Like

Installing voila with these commands:

    !pip install voila
    !jupyter serverextension enable voila --sys-prefix

fails in colab with this error:

        Enabling: voila
        - Writing config: /usr/etc/jupyter
            - Validating...
        Error loading server extension voila
              X is voila importable?

Any known solution?

1 Like

I wouldn’t have expected it to work in Colab. Remember: Google own fork of jupyter that’s not compatible with the rest of the world (sadly…)

1 Like

Sure this the closest how we get to address this presently.

ipywidgets are not supported in native colab. Try this:

Same problem about biased algorithms is discussed in this book:Algorithms of Oppression
Book by Safiya Noble.

1 Like

So, if face training with pictures of only one face, how to confirm it won’t get confused when tested with different faces? Wouldn’t it need to be trained by finding the difference between faces?

It couldn’t be trained solely on one person’s face. It would have to be a dataset that contains many pictures of the person you’re trying to identify and many pictures of other random people. My point was just that you don’t have to show it every other person in order to build a classifier that works.

1 Like

Is domain shift, same as concept drift?

2 Likes

I’ll plug my project which is looking at “out of domain” situation with different chess piece sets (as noted by @wdhorton) if you have any thought

In the example of data shift where the classifier goes from bears to raccoons should you do transfer learning from your previous model or retrain completely?