backprop

Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
○
codemeta.json file
○
.zenodo.json file
○
DOI references
○
Academic publication links
✓
Committers with academic emails
1 of 10 committers (10.0%) from academic institutions
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (15.1%) to scientific vocabulary

Keywords

bert fine-tuning image-classification language-model multilingual-models natural-language-processing nlp question-answering text-classification transfer-learning transformers

Keywords from Contributors

interpretability standardization animal hack

Last synced: 6 months ago · JSON representation

Repository

Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.

Basic Info

Host: GitHub
Owner: backprop-ai
License: other
Language: Python
Default Branch: main
Homepage: https://backprop.co
Size: 5.46 MB

Statistics

Stars: 242
Watchers: 15
Forks: 11
Open Issues: 5
Releases: 0

Topics

bert fine-tuning image-classification language-model multilingual-models natural-language-processing nlp question-answering text-classification transfer-learning transformers

Created over 5 years ago · Last pushed almost 5 years ago

Metadata Files

Readme License

README.md

Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.

Solve a variety of tasks with pre-trained models or finetune them in one line for your own tasks.

Out of the box tasks you can solve with Backprop:

Conversational question answering in English
Text Classification in 100+ languages
Image Classification
Text Vectorisation in 50+ languages
Image Vectorisation
Summarisation in English
Emotion detection in English
Text Generation

For more specific use cases, you can adapt a task with little data and a single line of code via finetuning.

Getting started

Installation

Install Backprop via PyPi:

bash pip install backprop

Basic task inference

Tasks act as interfaces that let you easily use a variety of supported models.

```python import backprop

context = "Take a look at the examples folder to see use cases!"

qa = backprop.QA()

Start building!

answer = qa("Where can I see what to build?", context)

print(answer)

Prints

"the examples folder" ```

You can run all tasks and models on your own machine, or in production with our inference API, simply by specifying your api_key.

See how to use all available tasks.

Basic finetuning and uploading

Each task implements finetuning that lets you adapt a model for your specific use case in a single line of code.

A finetuned model is easy to upload to production, letting you focus on building great applications.

```python import backprop

tg = backprop.TextGeneration("t5-small")

Any text works as training data

inp = ["I really liked the service I received!", "Meh, it was not impressive."] out = ["positive", "negative"]

Finetune with a single line of code

tg.finetune({"inputtext": inp, "outputtext": out})

Use your trained model

prediction = tg("I enjoyed it!")

print(prediction)

Prints

"positive"

Upload to Backprop for production ready inference

Describe your model

name = "t5-sentiment" description = "Predicts positive and negative sentiment"

tg.upload(name=name, description=description, api_key="abc") ```

See finetuning for other tasks.

Why Backprop?

No experience needed

Entrance to practical AI should be simple
Get state-of-the-art performance in your task without being an expert

Data is a bottleneck

Solve real world tasks without any data
With transfer learning, even a small amount of data can adapt a task to your niche requirements

There are an overwhelming amount of models

We offer a curated selection of the best open-source models and make them simple to use
A few general models can accomplish more with less optimisation

Deploying models cost effectively is hard work
- If our models suit your use case, no deployment is needed: just call our API
- Adapt and deploy your own model with just a few lines of code
- Our API scales, is always available, and you only pay for usage

Examples

Solve any text based task with Finetuning (Github, Colab)
Search for images using text (Github)
Finding answers from text (Github)
More finetuning and task examples

Documentation

Check out our docs for in-depth task inference and finetuning.

Model Hub

Curated list of state-of-the-art models.

Demos

Zero-shot image classification with CLIP.

Credits

Backprop relies on many great libraries to work, most notably:

Feedback

Found a bug or have ideas for new tasks and models? Open an issue.

Owner

Name: Backprop
Login: backprop-ai
Kind: organization
Email: hello@backprop.co

Website: https://backprop.co
Repositories: 2
Profile: https://github.com/backprop-ai

Making machine learning easy for every developer.

GitHub Events

Total

Last Year

Committers

Last synced: over 2 years ago

All Time

Total Commits: 188
Total Committers: 10
Avg Commits per committer: 18.8
Development Distribution Score (DDS): 0.404

Past Year

Commits: 0
Committers: 0
Avg Commits per committer: 0.0
Development Distribution Score (DDS): 0.0

Top Committers

Name	Email	Commits
Kristo Ojasaar	o**o@g**m	112
Owen LaCava	o**a@g**m	48
ojasaar	7****r	14
Cameron Wood	c**1@g**m	3
LaCava	l**a@W**n	3
github-actions[bot]	4****]	3
Ramon Catane	r**e@g**m	2
Eunho Lee	e**n@g**m	1
drycoco	k**5@s**k	1
RamonMamon	3****n	1

Committer Domains (Top 20 + Academic)

st-andrews.ac.uk: 1 wvyshps.lan: 1

Issues and Pull Requests

Last synced: 7 months ago

All Time

Total issues: 9
Total pull requests: 14
Average time to close issues: 3 days
Average time to close pull requests: about 19 hours
Total issue authors: 6
Total pull request authors: 4
Average comments per issue: 2.22
Average comments per pull request: 0.07
Merged pull requests: 14
Bot issues: 0
Bot pull requests: 0

Past Year

Issues: 0
Pull requests: 0
Average time to close issues: N/A
Average time to close pull requests: N/A
Issue authors: 0
Pull request authors: 0
Average comments per issue: 0
Average comments per pull request: 0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

chiragsanghvi10 (3)
singularity014 (2)
rishav1122 (1)
VaibhavDS19 (1)
karan-jgu (1)
Mattdinina (1)

Pull Request Authors

LaCavao (6)
ojasaar (6)
cameron-wood (1)
lucky7323 (1)

Top Labels

Issue Labels

Pull Request Labels

Packages

Total packages: 1
Total downloads:
- pypi 154 last-month

Total dependent packages: 0
Total dependent repositories: 2
Total versions: 17
Total maintainers: 1

pypi.org: backprop

Backprop

Homepage: https://github.com/backprop-ai/backprop
Documentation: https://backprop.readthedocs.io/en/latest/
License: Apache Software License
Latest release: 0.1.3
published almost 5 years ago

Versions: 17
Dependent Packages: 0
Dependent Repositories: 2
Downloads: 154 Last month

Rankings

Stargazers count: 4.3%

Dependent packages count: 10.1%

Forks count: 10.5%

Average: 11.3%

Dependent repos count: 11.6%

Downloads: 20.1%

Maintainers (1)

ojasaar

Last synced: 6 months ago

Dependencies

requirements.txt pypi

dill *
efficientnet_pytorch *
ftfy *
pytorch_lightning >=1.2.0,<1.3.0
sentence_transformers >=0.4.1.2
torch <1.8.0
torchtext <0.9.0
torchvision <0.9.0
transformers >=4.3.2,<4.5.0

setup.py pypi

dill *
efficientnet_pytorch *
ftfy *
pytorch_lightning >=1.2.0,<1.3.0
sentence_transformers >=0.4.1.2
torch <1.8.0
torchtext <0.9.0
torchvision <0.9.0
transformers >=4.3.2,<4.5.0