Finetuning any deep neural network for better embedding on neural search tasks
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.
finetuner.fit() - a one-liner that unlocks rich features such as siamese/triplet network, interactive labeling, layer pruning, weights freezing, dimensionality reduction.
How does it work
Install
Requires Python 3.7+ and one of PyTorch(>=1.9) or Tensorflow(>=2.5) or PaddlePaddle installed on Linux/MacOS.
pip install finetuner
Documentation
Usage
| Usage | Do you have an embedding model? | ||
|---|---|---|---|
| Yes | No | ||
| Do you have labeled data? | Yes | |
|
| No | |
|
|
🟠
Have embedding model and labeled data
Perfect! Now embed_model and labeled_data are given by you already, simply do:
import finetuner
finetuner.fit(
embed_model,
train_data=labeled_data
)
🟢
Have embedding model and unlabeled data
You have an embed_model to use, but no labeled data for finetuning this model. No worry, that's good enough already! You can use Finetuner to interactive label data and train embed_model as below:
import finetuner
finetuner.fit(
embed_model,
train_data=unlabeled_data,
interactive=True
)
🟡
Have general model and labeled data
You have a general_model which does not output embeddings. Luckily you provide some labeled_data for training. No worries, Finetuner can convert your model into an embedding model and train it via:
import finetuner
finetuner.fit(
general_model,
train_data=labeled_data,
to_embedding_model=True,
output_dim=100
)
🔵
Have general model and unlabeled data
You have a general_model which is not for embeddings. Meanwhile, you don't have labeled data for training. But no worries, Finetuner can help you train an embedding model with interactive labeling on-the-fly:
import finetuner
finetuner.fit(
general_model,
train_data=unlabeled_data,
interactive=True,
to_embedding_model=True,
output_dim=100
)
Finetuning ResNet50 on CelebA
⚡ To get the best experience, you will need a GPU-machine for this example. For CPU users, we provide finetuning a MLP on FashionMNIST and finetuning a Bi-LSTM on CovidQA that run out the box on low-profile machines. Check out more examples in our docs!
- Download CelebA-small dataset (7.7MB) and decompress it to
'./img_align_celeba'. Full dataset can be found here. - Finetuner accepts Jina
DocumentArray/DocumentArrayMemmap, so we load CelebA image into this format using a generator:from jina.types.document.generators import from_files def data_gen(): for d in from_files('./img_align_celeba/*.jpg', size=100, to_dataturi=True): d.convert_image_datauri_to_blob(color_axis=0) # `color_axis=-1` for TF/Keras users yield d
- Load pretrained ResNet50 using PyTorch/Keras/Paddle:
- PyTorch
import torchvision model = torchvision.models.resnet50(pretrained=True)
- Keras
import tensorflow as tf model = tf.keras.applications.resnet50.ResNet50(weights='imagenet')
- Paddle
import paddle model = paddle.vision.models.resnet50(pretrained=True)
- PyTorch
- Start the Finetuner:
import finetuner finetuner.fit( model=model, interactive=True, train_data=data_gen, freeze=True, to_embedding_model=True, input_size=(3, 224, 224), output_dim=100 )
- After downloading the model and loading the data (takes ~20s depending on your network/CPU/GPU), your browser will open the Labeler UI as below. You can now label the relevance of celebrity faces via mouse/keyboard. The ResNet50 model will get finetuned and improved as you are labeling. If you are running this example on a CPU machine, it may take up to 20 seconds for each labeling round.
Support
- Use Discussions to talk about your use cases, questions, and support queries.
- Join our Slack community and chat with other Jina community members about ideas.
- Join our Engineering All Hands meet-up to discuss your use case and learn Jina's new features.
- When? The second Tuesday of every month
- Where? Zoom (see our public events calendar/.ical) and live stream on YouTube
- Subscribe to the latest video tutorials on our YouTube channel
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.
(embedding is here just a 128-dim vector). My model is PyTorch 2 linear layers that inference on that embedding and spit out 128 dimensional vector.
139 Jan 1, 2023
93 Sep 30, 2022
694 Nov 23, 2022
290 Dec 24, 2022
1k Dec 13, 2022
479 Dec 8, 2022
1.8k Jan 4, 2023
4 Jul 12, 2022
562 Dec 27, 2022
180 Jan 5, 2023
97 Dec 23, 2022
0 May 4, 2022
214 Jan 8, 2023
13 Nov 4, 2022
291 Nov 18, 2022
122 Dec 7, 2022
1.4k Jan 5, 2023
2.8k Dec 29, 2022