Aurélien Geron comments

Results 284 comments of


                                            Aurélien Geron

[BUG] Chap 3 SVC use OvR by default instead of OvO

Yes, exactly. The [source code is available here](https://github.com/scikit-learn/scikit-learn/blob/642127806a830346886a0337fcbefedc871159c0/sklearn/utils/multiclass.py#L443). In short, when you call `predict()` to classify an instance, Scikit-Learn calls libsvm, which makes 45 predictions (one per pair of classes,...

[BUG] French version, 2d ed., p. 4, $ python3 -m ipykernel install --user --name=python3

Thanks @Eleuthere for your kind words and your feedback, much appreciated! However, I haven't been able to reproduce the issue. I just tried running the command, and it worked fine...

[BUG] French version, 2d ed., p. 4, $ python3 -m ipykernel install --user --name=python3

Bonjour Jean-Marie, Je suis ravi que mon livre vous soit utile ! Ah je vois où est le problème: quand on passe des arguments en ligne de commande, il ne...

[BUG] French version, 2d ed., p. 4, $ python3 -m ipykernel install --user --name=python3

Ah merci beaucoup, c'est une erreur dans la version française apparemment, je vais le signaler à l'éditeur (Dunod). 👍

[QUESTION] How exactly does auxiliary output in a NN help regularize

Hi @Ruhil-DS , Suppose the neural net's main task is to classify images of cats and dogs. Just two classes. Perhaps in this particular training set, most dogs have a...

16_nlp_with_rnns_and_attention.ipynb cell #18 ---model = keras.models.Sequential... ---generates NotImplementedError: Cannot convert a symbolic Tensor (gru_2/strided_slice:0) to a numpy array

Hi @sulu987 , I cannot reproduce this issue, everything works fine on my system and [on Colab](https://colab.research.google.com/github/ageron/handson-ml2/blob/master/16_nlp_with_rnns_and_attention.ipynb). Questions: * Are you running on Colab? Or Kaggle? Or your own system?...

16_nlp_with_rnns_and_attention.ipynb cell #18 ---model = keras.models.Sequential... ---generates NotImplementedError: Cannot convert a symbolic Tensor (gru_2/strided_slice:0) to a numpy array

Hi @sulu987 , I'm glad things work now! Could you please explain what fixed the issue, in case others run into the same issue? Thanks!

16_nlp_with_rnns_and_attention.ipynb cell #18 ---model = keras.models.Sequential... ---generates NotImplementedError: Cannot convert a symbolic Tensor (gru_2/strided_slice:0) to a numpy array

Hi @hafiz031 , I've tried to reproduce this issue, but the code just works fine. Here's a [notebook containing your StackOverflow code example](https://colab.research.google.com/gist/ageron/4d1129328dacd677972efc72d3470d5a/homl2-issue-439.ipynb) (I just added a couple extra cells...

16_nlp_with_rnns_and_attention.ipynb cell #18 ---model = keras.models.Sequential... ---generates NotImplementedError: Cannot convert a symbolic Tensor (gru_2/strided_slice:0) to a numpy array

Hi @hafiz031 , That's interesting, thanks for your feedback. I tried running the [Colab Notebook](https://colab.research.google.com/gist/ageron/4d1129328dacd677972efc72d3470d5a/homl2-issue-439.ipynb) containing your code, using with a GPU runtime, but it worked fine. I even tried...

[IDEA] Introduction about AutoML

Hi @Kirushikesh , thanks for your suggestion. I'm currently traveling for the next few weeks, but I'll check this out when I get back. I believe I added a note...