This project is the code repository for Natural Language Processing with TensorFlow, Second Edition.

You can run these notebooks on cloud platforms like Google Colab or your local machine. Note that some chapters require a GPU to run in a reasonable amount of time, so we recommend one of the cloud platforms as they come pre-installed with CUDA.

Chapters	Colab	Kaggle	Gradient	StudioLab
Understanding TensorFlow 2 tensorflow_introduction.ipynb
Word2vec – Learning Word Embeddings ch3_word2vec.ipynb ch3_wordnet.ipynb
Advanced Word Vector Algorithms ch4_document_classification.ipynb ch4_elmo_embeddings.ipynb ch4_glove.ipynb
Sentence Classification with Convolution Neural Networks ch5_cnn_sentence_classification.ipynb ch5_image_classification_fashion_mnist.ipynb
Recurrent Neural Networks ch06_rnns_for_named_entity_recognition.ipynb
Applications of LSTM – Generating Text ch08_lstms_for_text_generation.ipynb
Sequence-to-Sequence Learning – Neural Machine Translation ch09_seq2seq.ipynb
Transformers ch10_transformers.ipynb
Image captioning with Transformers ch11_image_captions.ipynb
Appendix tensorboard_word_embeddings.ipynb

• Install the latest NVIDIA driver for your GPU from this page
• Install CUDA 10.2 (TensorFlow 2.3)
• Setup CuDNN
• Make sure your $PATH variable contains the path to the bin folder of cuda (e.g. On Windows - C:\CUDA\v10.2\bin)
  • On UNIX - Set LD_LIBRARY_PATH to lib64 folder (e.g. /usr/local/cuda-10.2/lib64)

• Install Anaconda
• Open up Anaconda Prompt
• Setup a conda virtual environment with conda create -n packt.nlp.2 python=3.6
• Activate the environment with conda activate packt.nlp.tf2
• Install the required libraries using pip install -r requirements.txt

• For some plotting capability provided in TensorFlow/Keras, you have installed a Python package called graphviz. You might need to add the path to this library (e.g. <path to Anaconda>\envs\packt.nlp.tf2\Library\bin\graphviz if you used Anaconda installation)

Now you are ready to run the Jupyter notebook server, allowing you to run the notebooks provided in the code repository.

• Open up the command line terminal and activate the virtual environment packt.nlp.tf2 if you haven't already
• Go in to the directory you downloaded code to using cd in the CLI (e.g. cd C:\Users\<user>\Documents\code\packt_nlp_tensorflow_2)
• Run jupyter notebook in the CLI
• This should open up the jupyter notebook server's landing page on your default browser
• Now you can navigate the folder structure within that directory, open any notebook and run it.