Adaptive Image Intelligence Architecture
Go to file
Falko Victor Habel 8d05481498 Merge pull request 'feat/fix_saving' (#13) from feat/fix_saving into main
Reviewed-on: #13
2025-03-01 21:54:36 +00:00
src/aiia updated version to support proper saving when pretraining 2025-02-27 18:56:42 +01:00
.gitignore Initial commit 2025-01-07 10:56:41 +00:00
LICENSE Initial commit 2025-01-07 10:56:41 +00:00
MANIFEST.in added first pip install version 0.1 2025-01-28 10:58:33 +01:00
README.md fixed setup with correct naming 2025-02-27 21:56:50 +01:00
example.py updated version to support proper saving when pretraining 2025-02-27 18:56:42 +01:00
pyproject.toml fixed project files 2025-02-27 22:00:48 +01:00
requirements.txt fixed project files 2025-02-27 22:00:48 +01:00
setup.cfg fixed licence 2025-02-27 21:57:39 +01:00
setup.py fixed model loading due to a bug 2025-02-24 14:13:10 +01:00

README.md

AIIA

Installation

Install via pip

To install the package directly from the Git repository using pip, run:

pip install git+https://gitea.fabelous.app/Machine-Learning/AIIA.git

This command will clone the repository and install the package along with its dependencies.

Additional Notes

  • Ensure you have git installed on your system.
  • Make sure pip is up-to-date. You can update it using:
    pip install --upgrade pip
    

That's it! You should now have the AIIA package installed and ready to use.

Example Usage:

from aiia.model import AIIABase
from aiia.model import AIIAConfig
from aiia.pretrain import Pretrainer

# Create your model
config = AIIAConfig(model_name="AIIA-Base-512x20k")
model = AIIABase(config)

# Initialize pretrainer with the model
pretrainer = Pretrainer(model, learning_rate=1e-4)

# List of dataset paths
dataset_paths = [
    "/path/to/dataset1.parquet",
    "/path/to/dataset2.parquet"
]

# Start training with multiple datasets
pretrainer.train(
    dataset_paths=dataset_paths,
    num_epochs=10,
    batch_size=2,
    sample_size=10000
)