Python-Deep-Learning icon indicating copy to clipboard operation
Python-Deep-Learning copied to clipboard

D-Lab's 6 hour introduction to deep learning in Python. Learn how to create and train neural networks using Tensorflow and Keras.

Results 17 Python-Deep-Learning issues
Sort by recently updated
recently updated
newest added

For some lines of importing packages, tensorflow needs to be added before keras change "from keras.utils import to_categorical" to -> "from tensorflow.keras.utils import to_categorical"

The instruction does not have installation instruction for tensor flow for Datahub and Datahub does not seem to have Tensorflow installed as default (Either instruction or data hub need to...

When the instructor is demonstrating challenge 2, one participant noted that they are not getting the same results. This is perhaps due to not setting a random seed that makes...

if you look at the GitHub repo, the solutions for notebook 2 are missing. I thought it was just an issue for me but it's for everyone.

Slightly before challenge 2, we are running neural network models and looking at different ways of changing training and validation accuracy. Everyone is getting a different graph for the validation...

Why do we not add an input shape throughout

In Challenge 2 in Notebook 3 (Convolutional Neural Networks), it's unclear where exactly students are supposed to make changes to the code. The challenge should be dropped or else modified.

It would be great to provide students with more of a conceptual take of what neural nets are. We had some slides in the previous version of the project. Is...

can we get a link to the google colab in lessons 2 and 3 and the solutions? we had to put the repo url into google collab

One question that I keep getting from students is why do we choose certain hyperparameters. I keep explaining that it's an art form also there's a lot of research around...