IMAGE CAPTIONING ANNOTATION with Prodigy & PyTorch: custom scriptable machine learning annotation
Prodigy is a modern annotation tool for collecting training data for machine learning models, developed by the makers of spaCy. In this video, we'll show you how you can use Prodigy to script fully custom annotation workflows in Python, how to plug in your own machine learning models and how to mix and match different interfaces for your specific use case. We'll create a dataset of image captions, use an image captioning model implemented in PyTorch to suggest captions and perform error anylsis to find out what the model is getting right, and where it needs improvement.
STEP BY STEP
01:59 – Create a recipe for manual image captioning
13:26 – Plug in an image captioning model implemented in PyTorch and correct its output
19:41 – Add callback to count changed captions and output results
26:33 - Add workflow for error analysis and reviewing annotations
PRODIGY
● Website & docs: https://prodi.gy
● Live demo: https://prodi.gy/demo
● Custom recipes docs: https://prodi.gy/docs/custom-recipes
● Forum: https://support.prodi.gy
● Recipe scripts: https://github.com/explosion/prodigy-recipes
THIS TUTORIAL
● Code: https://github.com/explosion/prodigy-recipes/tree/master/image/image_caption
● PyTorch tutorial & model: https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/03-advanced/image_captioning
● Images dataset: https://www.kaggle.com/alessiocorrado99/animals10
FOLLOW US
● Ines Montani: https://twitter.com/_inesmontani
● Explosion: https://twitter.com/explosion_ai
CREDITS
● Thumbnail cat image #1: https://unsplash.com/photos/E9kVmtiqqGE
● Thumbnail cat image #2: https://unsplash.com/photos/_Mty3g9XWr0
Видео IMAGE CAPTIONING ANNOTATION with Prodigy & PyTorch: custom scriptable machine learning annotation канала Explosion
STEP BY STEP
01:59 – Create a recipe for manual image captioning
13:26 – Plug in an image captioning model implemented in PyTorch and correct its output
19:41 – Add callback to count changed captions and output results
26:33 - Add workflow for error analysis and reviewing annotations
PRODIGY
● Website & docs: https://prodi.gy
● Live demo: https://prodi.gy/demo
● Custom recipes docs: https://prodi.gy/docs/custom-recipes
● Forum: https://support.prodi.gy
● Recipe scripts: https://github.com/explosion/prodigy-recipes
THIS TUTORIAL
● Code: https://github.com/explosion/prodigy-recipes/tree/master/image/image_caption
● PyTorch tutorial & model: https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/03-advanced/image_captioning
● Images dataset: https://www.kaggle.com/alessiocorrado99/animals10
FOLLOW US
● Ines Montani: https://twitter.com/_inesmontani
● Explosion: https://twitter.com/explosion_ai
CREDITS
● Thumbnail cat image #1: https://unsplash.com/photos/E9kVmtiqqGE
● Thumbnail cat image #2: https://unsplash.com/photos/_Mty3g9XWr0
Видео IMAGE CAPTIONING ANNOTATION with Prodigy & PyTorch: custom scriptable machine learning annotation канала Explosion
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![Face Detection on Custom Dataset with Detectron2 & PyTorch using Python | Object Detection Tutorial](https://i.ytimg.com/vi/8eLHZ0R5nHQ/default.jpg)
![FAQ #1: Tips & tricks for NLP, annotation & training with Prodigy and spaCy](https://i.ytimg.com/vi/tMAU3gLbKII/default.jpg)
![Pytorch Image Captioning Tutorial](https://i.ytimg.com/vi/y2BaTt1fxJU/default.jpg)
![But what is a Neural Network? | Deep learning, chapter 1](https://i.ytimg.com/vi/aircAruvnKk/default.jpg)
![How we teach computers to understand pictures | Fei Fei Li](https://i.ytimg.com/vi/40riCqvRoMs/default.jpg)
![PRODIGY v1.10: Dependencies, relations, audio, video, extended NER and image annotation & lots more](https://i.ytimg.com/vi/KCrIa538u4I/default.jpg)
![Show, Attend and Tell](https://i.ytimg.com/vi/bBMxSg3c_6M/default.jpg)
![From Research to Production with PyTorch](https://i.ytimg.com/vi/EkELQw9tdWE/default.jpg)
![Python Tutorial: if __name__ == '__main__'](https://i.ytimg.com/vi/sugvnHA7ElY/default.jpg)
![NLP avanzado con spaCy · Un curso en línea gratis](https://i.ytimg.com/vi/RNiLVCE5d4k/default.jpg)
![Matthew Honnibal & Ines Montani: spaCy and Explosion: past, present & future (spaCy IRL 2019)](https://i.ytimg.com/vi/Jk9y17lvltY/default.jpg)
![Intro to NLP with spaCy (1): Detecting programming languages | Episode 1: Data exploration](https://i.ytimg.com/vi/WnGPv6HnBok/default.jpg)
![15 1 attention models, image captioning, machine translation I](https://i.ytimg.com/vi/mlLiy8DrUcc/default.jpg)
![How to run PyTorch models in the browser with ONNX.js](https://i.ytimg.com/vi/Vs730jsRgO8/default.jpg)
![Training a custom ENTITY LINKING model with spaCy](https://i.ytimg.com/vi/8u57WSXVpmw/default.jpg)
![Image Classification using CNN from Scratch in Pytorch- Part 1 Training](https://i.ytimg.com/vi/9OHlgDjaE2I/default.jpg)
![Research to Production: PyTorch JIT/TorchScript Updates - Michael Suo](https://i.ytimg.com/vi/St3gdHJzic0/default.jpg)
![Robert Meyer - Analysing user comments with Doc2Vec and Machine Learning classification](https://i.ytimg.com/vi/zFScws0mb7M/default.jpg)
![Training a NAMED ENTITY RECOGNITION MODEL with Prodigy and Transfer Learning](https://i.ytimg.com/vi/59BKHO_xBPA/default.jpg)
![TRAINING AN INSULTS CLASSIFIER with Prodigy in ~1 hour](https://i.ytimg.com/vi/5di0KlKl0fE/default.jpg)