Davide Fiocco davidefiocco
davidefiocco
/ dataset.jsonl
Last active
July 7, 2022 17:20
Example prodigy recipe to use a zero-shot classifier to pre-classify examples when performing labeling for text classification (see https://support.prodi.gy/t/can-one-leverage-zero-shot-classifiers-for-textcat-tasks/4885)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| {"text":"Spam spam lovely spam!"} | |
| {"text":"I like scrambled eggs."} | |
| {"text":"I prefer spam!"} |
davidefiocco
/ text-classification-in-pytorch-to-refactor-with-pytorch-lightning.ipynb
Last active
March 1, 2021 22:03
Text classification in PyTorch to refactor with PyTorch lightning.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
davidefiocco
/ text-classification-in-pytorch-to-refactor-with-petastorm.ipynb
Last active
February 15, 2021 17:58
Text classification in PyTorch to refactor with petastorm.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
davidefiocco
/ copyedits.jsonl
Created
November 5, 2020 17:59
Prodigy recipe to categorize differences in text
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| {"removed":"These results suggested that the distribution of bacterial communities was driven more by sample types than the separate caves from which samples were collected.","added":"These results suggest that the distribution of bacterial communities is driven more by sample types than the separate caves from which samples were collected.","meta":{"score":1}} |
davidefiocco
/ azureml-logging-on-transformers.ipynb
Created
October 23, 2020 16:04
AzureML logging on transformers.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| gst-launch-1.0 v4l2src device=/dev/video0 ! xvimagesink |
davidefiocco
/ test_transforms.py
Created
May 19, 2020 12:18
Test torchvision tranforms on a bunch of images
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from torchvision import datasets, models, transforms | |
| from PIL import Image | |
| import torch | |
| import matplotlib.pyplot as plt | |
| from pathlib import Path | |
| images = list(Path('../foo').glob('**/*.*')) | |
| example = images.pop() | |
| img = Image.open(example).convert('RGB') |
davidefiocco
/ copy-of-interpretation.ipynb
Last active
August 6, 2022 03:07
@NarineK solution for BERT interpretation in https://github.com/pytorch/captum/issues/311#issuecomment-612460705
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
NewerOlder