Skip to main content

Finetuner allows one to tune the weights of any deep neural network for better embedding on search tasks.

Project description

Finetuner logo: Finetuner allows one to finetune any deep Neural Network for better embedding on search tasks. It accompanies Jina to deliver the last mile of performance-tuning for neural search applications.

Finetuning any deep neural network for better embedding on neural search tasks

Python 3.7 3.8 3.9 PyPI

Finetuner allows one to tune the weights of any deep neural network for better embeddings on search tasks. It accompanies Jina to deliver the last mile of performance for domain-specific neural search applications.

🎛 Designed for finetuning: a human-in-the-loop deep learning tool for leveling up your pretrained models in domain-specific neural search applications.

🔱 Powerful yet intuitive: all you need is finetuner.fit() - a one-liner that unlocks rich features such as siamese/triplet network, metric learning, self-supervised pretraining, layer pruning, weights freezing, dimensionality reduction.

⚛️ Framework-agnostic: promise an identical API & user experience on PyTorch, Tensorflow/Keras and PaddlePaddle deep learning backends.

🧈 DocArray integration: buttery smooth integration with DocArray, reducing the cost of context-switch between experiment and production.

How does it work

Python 3.7 3.8 3.9

Install

Requires Python 3.7+ and one of PyTorch(>=1.9) or Tensorflow(>=2.5) or PaddlePaddle installed on Linux/MacOS.

pip install finetuner

Finetuning ResNet50 on CelebA

  1. Download CelebA-small dataset (7.7MB) and decompress it to './img_align_celeba'. Full dataset can be found here.
  2. Finetuner accepts docarray DocumentArray, so we load CelebA image into this format using a generator:
    from docarray import DocumentArray
    
    # please change the file path to your data path
    data = DocumentArray.from_files('img_align_celeba/*.jpg')
    
    
    def preproc(doc):
        return (
            doc.load_uri_to_image_tensor(224, 224)
            .set_image_tensor_normalization()
            .set_image_tensor_channel_axis(-1, 0)
        )  # No need for normalization and changing channel axes line if you are using tf/keras
    
    
    data.apply(preproc)
    
  3. Load pretrained ResNet18 using PyTorch/Keras/Paddle:
    • PyTorch
      import torchvision
      resnet = torchvision.models.resnet50(pretrained=True)
      
    • Keras
      import tensorflow as tf
      resnet = tf.keras.applications.resnet50.ResNet50(weights='imagenet')
      
    • Paddle
      import paddle
      resnet = paddle.vision.models.resnet50(pretrained=True)
      
  4. Start the Finetuner:
    import finetuner as ft
    
    tuned_model = ft.fit(
        model=resnet,
        train_data=data,
        loss='TripletLoss',
        epochs=20,
        device='cuda',
        batch_size=128,
        to_embedding_model=True,
        input_size=(3, 224, 224), # for keras use (224, 224, 3)
        freeze=False,
    )
    

Support

Join Us

Finetuner is backed by Jina AI and licensed under Apache-2.0. We are actively hiring AI engineers, solution engineers to build the next neural search ecosystem in opensource.

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

finetuner-0.4.2.dev13.tar.gz (59.2 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page