Files
dragonpilot/tinygrad_repo/docs/showcase.md
Vehicle Researcher dd778596b7 openpilot v0.9.8 release
date: 2025-03-15T21:10:51
master commit: fb7b9c0f9420d228f03362970ebcfb7237095cf3
2025-03-18 10:05:17 -07:00

1.6 KiB

Showcase

Despite being a tiny library, tinygrad is capable of doing a lot of things. From state-of-the-art vision to state-of-the-art language models.

Vision

EfficientNet

You can either pass in the URL of a picture to discover what it is:

python3 examples/efficientnet.py ./test/models/efficientnet/Chicken.jpg

Or, if you have a camera and OpenCV installed, you can detect what is in front of you:

python3 examples/efficientnet.py webcam

YOLOv8

Take a look at yolov8.py.

yolov8 by tinygrad

Audio

Whisper

Take a look at whisper.py. You need pyaudio and torchaudio installed.

SMALL=1 python3 examples/whisper.py

Generative

Stable Diffusion

python3 examples/stable_diffusion.py

a horse sized cat eating a bagel

"a horse sized cat eating a bagel"

LLaMA

You will need to download and put the weights into the weights/LLaMA directory, which may need to be created.

Then you can have a chat with Stacy:

python3 examples/llama.py

Conversation

Make sure you have espeak installed and PHONEMIZER_ESPEAK_LIBRARY set.

Then you can talk to Stacy:

python3 examples/conversation.py