Use Florence 2 to auto-label data for use in training fine-tuned object detection models.
Project description
Autodistill Florence 2 Module
This repository contains the code supporting the CLIP base model for use with Autodistill.
Florence 2, introduced in the paper Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks is a multimodal vision model.
You can use Florence 2 to generate object detection annotations for use in training smaller object detection models with Autodistill.
Read the full Autodistill documentation.
Read the Florence 2 Autodistill documentation.
Installation
To use Florence 2 with Autodistill, you need to install the following dependency:
pip3 install autodistill-florence-2
Quickstart (Inference from Base Weights)
from autodistill_florence_2 import Florence2
from autodistill.detection import DetectionOntology
from PIL import Image
# define an ontology to map class names to our Florence 2 prompt
# the ontology dictionary has the format {caption: class}
# where caption is the prompt sent to the base model, and class is the label that will
# be saved for that caption in the generated annotations
# then, load the model
base_model = Florence2(
ontology=CaptionOntology(
{
"person": "person",
"a forklift": "forklift"
}
)
)
image = Image.open("image.jpeg")
result = base_model.predict('image.jpeg')
bounding_box_annotator = sv.BoundingBoxAnnotator()
annotated_frame = bounding_box_annotator.annotate(
scene=image.copy(),
detections=detections
)
sv.plot_image(image=annotated_frame, size=(16, 16))
# label a dataset
base_model.label("./context_images", extension=".jpeg")
Quickstart (Fine-Tune)
from autodistill_florence_2 import Florence2Trainer
model = Florence2Trainer("dataset")
model.train(dataset.location, epochs=10)
License
This project is licensed under an MIT license. See the Florence 2 license for more information about the Florence 2 model license.
🏆 Contributing
We love your input! Please see the core Autodistill contributing guide to get started. Thank you 🙏 to all our contributors!
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for autodistill_florence_2-0.1.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 16574ed62f7fcc30df3284cd7324e2aef9cc994500154105daf6ac78ea8da209 |
|
MD5 | 676d5f1cd7e7e4cf8193eebd50b1163d |
|
BLAKE2b-256 | f4284324103897a3f7043d1c896cc59025b917a5bfef05e587223e99eaa102f5 |
Hashes for autodistill_florence_2-0.1.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | c4a559748a94d652c230950ab7f5e2e3b952f49b1dade38fd841e73e088053bc |
|
MD5 | d1acd1e0d366d6292ad14d427a6c7af9 |
|
BLAKE2b-256 | 186b05581c71620306e098ac5e27d3420741a79e55dddcc74d44c399c06c388b |