6.4 Implementing a 1D convnet for the IMDB dataset

fchollet / deep-learning-with-python-notebooks

Jupyter notebooks for the code samples of the book "Deep Learning with Python"

MIT License

18.17k stars 8.53k forks source link

Open yurisolovev opened 4 years ago

yurisolovev commented 4 years ago

In the Dense layer, a sigmoidal activation function must be added, since we solve the classification problem, right?

oren0e commented 4 years ago

Yep, I believe this is a mistake in the book. Until I added the sigmoid activation the loss wasn't changing with the epochs.