Image utility library for Deep Learning
Project description
chitra
What is chitra?
chitra (चित्र) is an image utility library for Deep Learning tasks. (It is not image-processing library)
chitra reduces image data loading boilerplates for classification and object-detection.
It can also generate bounding-boxes from the annotated dataset.
If you have more use cases please raise an issue with the feature you want.
Installation
Using pip (recommended)
pip install -U chitra
From source
git clone https://github.com/aniketmaurya/chitra.git
cd chitra
pip install -e .
Usage
Loading data for image classification
import numpy as np
import tensorflow as tf
import chitra
from chitra.dataloader import Clf, show_batch
import matplotlib.pyplot as plt
path = '/Users/aniket/Pictures/data/train'
clf_dl = Clf()
data = clf_dl.from_folder(path, target_shape=(224, 224))
clf_dl.show_batch(8, figsize=(8,8))
CLASSES ENCODED: {'cat': 0, 'dog': 1}
for e in data.take(1):
image = e[0].numpy().astype('uint8')
label = e[1].numpy()
plt.imshow(image)
plt.show()
Visualization
Image annotation
Thanks to fizyr keras-retinanet.
from chitra.visualization import draw_annotations
labels = np.array([label])
bbox = np.array([[30, 50, 170, 190]])
label_to_name = lambda x: 'Cat' if x==0 else 'Dog'
draw_annotations(image, ({'bboxes': bbox, 'labels':labels,}), label_to_name=label_to_name)
plt.imshow(image)
plt.show()
Utils
from chitra.utils import limit_gpu
# limit the amount of GPU required for your training
limit_gpu(gpu_id=0, memory_limit=1024*2)
No GPU found in your system!
Contributing
Contributions of any kind are welcome. Please check the Contributing Guidelines before contributing.
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
chitra-0.0.14.tar.gz
(15.1 kB
view hashes)
Built Distribution
chitra-0.0.14-py3-none-any.whl
(15.4 kB
view hashes)