2019 (March) Converting Code to Run on TensorFlow 2.0 (including Keras)

Опубликовано: 12 Октябрь 2024
на канале: Jeff Heaton

7,408

100

I took a quick look at TensorFlow 2.0 to see how many of the examples from my course (Applications of Deep Neural Networks) would get broken. Since I am using Keras, it was not too bad. In this video I do a quick install of TensorFlow 2.0 and show some of the code changes that are needed to upgrade to TensorFlow 2.0.

Commands referred to in the video:

conda install -y jupyter
conda install -y scipy
pip install --upgrade sklearn
conda install -y pandas
conda install -y pandas-datareader
conda install -y matplotlib
conda install -y pillow
conda install -y upgrade requests
conda install -y upgrade h5py
conda install -y nb_conda

CPU
pip install tensorflow==2.0.0-alpha0
GPU
pip install tensorflow-gpu==2.0.0-alpha0

python -m ipykernel install --user --name tensorflow-2.0 --display-name "Python 3.6 (tensorflow-2.0)"