GluonNLP: Your Choice of Deep Learning for NLP

In the world of Natural Language Processing (NLP), having the right toolkit can make all the difference. GluonNLP is here to streamline your experience, offering a comprehensive set of tools to help you load, process, and train models on text data with unparalleled ease!

Features You’ll Love

• Easy-to-use Text Processing Tools and Modular APIs
• Pretrained Model Zoo
• Write Models with a Numpy-like API
• Fast Inference via Apache TVM (incubating) (Experimental)
• AWS Integration via SageMaker

Installation Guide

Ready to get started? Let’s install GluonNLP step by step.

Step 1: Install MXNet

You need to install the MXNet 2 release (e.g., MXNet 2 Alpha). Depending on your system’s configuration, choose one of the following commands:

# Install the version with CUDA 10.2
python3 -m pip install -U --pre mxnet-cu102=2.0.0a

# Install the version with CUDA 11
python3 -m pip install -U --pre mxnet-cu110=2.0.0a

# Install the CPU-only version
python3 -m pip install -U --pre mxnet=2.0.0a

Step 2: Install GluonNLP

Now, it’s time to install GluonNLP itself:

python3 -m pip install -U -e .

Want all the extra goodies? Use:

python3 -m pip install -U -e .[extras]

If you encounter permission issues, install in the user folder:

python3 -m pip install -U -e . --user

Windows Users

We recommend using the Windows Subsystem for Linux for installation.

Accessing Command-line Toolkits

For engineers and researchers alike, GluonNLP offers command-line toolkits for downloading and processing NLP datasets. Here’s how to access them:

# CLI for downloading and preparing the dataset
nlp_data help

# CLI for accessing common data processing scripts
nlp_process help

# Access toolkits using python -m
python3 -m gluonnlp.cli.data help
python3 -m gluonnlp.cli.process help

Running Unittests

To ensure everything is working well, don’t forget to run the unit tests available in the tests directory.

Using Docker

For the ultimate development environment, use Docker to get GluonNLP running smoothly:

GPU Instance

docker pull gluonaigluon-nlp:gpu-latest
docker run --gpus all --rm -it -p 8888:8888 -p 8787:8787 -p 8786:8786 --shm-size=2g gluonaigluon-nlp:gpu-latest

CPU Instance

docker pull gluonaigluon-nlp:cpu-latest
docker run --rm -it -p 8888:8888 -p 8787:8787 -p 8786:8786 --shm-size=2g gluonaigluon-nlp:cpu-latest

Troubleshooting Tips

If you encounter any issues, consider the following troubleshooting steps:

• Verify that your Python version is compatible.
• Check your environment dependencies carefully.
• Review your Docker setup if using containerized installations.

For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.

Conclusion

At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.