Skip to main content
100%

configure random transformations and normalization operations to be done on your image data during training

✓ Published0🌍 Public
Aabehmiel
Last edited Aug 3, 2017
Created on Aug 3, 2017

The example demonstrates how Keras’s `ImageDataGenerator` applies random geometric transformations and normalization to a single input image, producing a grid of augmented variations saved as JPEG files. It shows the effects of rotation, width and height shifts, shear, zoom, and horizontal flipping on a cat photo, with pixel fill mode set to nearest. The code loads an image via `load_img`, converts it to a NumPy array with `img_to_array`, reshapes it into a batch, and then uses the generator’s `.flow()` method to generate and save 20 preview images to a directory. The approach relies entirely on Keras’s preprocessing API, with no custom data source or rendering.

AI-generated description

Similar vizzes

Loading thumbnail…

stroke + keras augmentation

This example demonstrates data augmentation for a convolutional neural network that classifies stroke-related images into two categories. It trains a Keras Sequential model with Conv2D, MaxPooling2D, Dropout, and LeakyReLU layers, using an ImageDataGenerator to apply shear, zoom, and horizontal flip transformations to grayscale images. The code also uses a ModelCheckpoint callback to save the best model based on validation accuracy, processing batches of 256x256 images from training and validation directories.

Aakeshavan
60% match
Loading thumbnail…

Gist f8ef22f4884653740625923059e1acfb

This example processes brain scan sprite images for use in a web-based visualization. It loads PNG files from a local directory, replaces pure black pixels with white, and then applies histogram equalization and autocontrast using Pillow’s `ImageOps` and `ImageEnhance`. The cleaned images are saved to a new path, with the code iterating over a list of subject IDs read from a text file via `np.genfromtxt`. It reports completion or errors for each subject, demonstrating a batch image-preprocessing pipeline for preparing neuroimaging data.

Aakeshavan
53% match
Loading thumbnail…

Image Magick Cheat Sheet - Fun and easy picture editing in Linux command lIne

This example is a cheat sheet for using ImageMagick from the Linux command line, presented as a Jupyter notebook. It demonstrates two common image-processing tasks: resizing an image while preserving its aspect ratio via the `convert` command with the `-resize` flag, and creating an animated GIF from a sequence of PNG files using `-delay` and `-loop` options. The code relies on the ImageMagick `convert` utility and includes links to external tutorials for reference.

PP3nny
53% match
Loading thumbnail…

Gist 50acac748fdb4324a0dc2759fb6fce55

This notebook builds and trains a convolutional neural network for binary image classification using Keras with TensorFlow. It defines a Sequential model with Conv2D, LeakyReLU, MaxPooling2D, Dropout, Flatten, and Dense layers, then compiles it with categorical crossentropy and the Adam optimizer. The model trains on pre-loaded NumPy arrays from seed-0-train.npz, with validation on seed-0-val.npz, and uses ModelCheckpoint to save the best weights based on validation accuracy.

Aakeshavan
53% match
Loading thumbnail…

Illusion images

The example shows a collection of small, repeating portrait images that initially appear to form a single large face, an optical illusion created through careful arrangement. The visualization uses a grid of individual portrait thumbnails, each rendered as a separate image element, to collectively build a larger, recognizable portrait. The code employs the Canvas API’s `drawImage` method to place each thumbnail at a specific position, while the overall layout is computed using a custom algorithm that maps the target face’s pixel data—accessed via `getImageData`—to determine the appropriate size and color of each tile. The source images are drawn from a local set of portraits, and the effect relies on adjusting each tile’s average color to match the corresponding area of the target portrait.

AAlainRo
52% match
Loading thumbnail…

Generate image from drawing https://py.plainenglish.io/convert-a-photo-to-pencil-sketch-using-python-in-12-lines-of-code-4346426256d4

This example converts a photo into a pencil-sketch style image. It reads an input image file, transforms it through grayscale conversion, inversion, Gaussian blurring, and final blending to produce a sketch-like output saved as a new file. The code relies on OpenCV’s `cv2.imread`, `cv2.cvtColor`, `cv2.GaussianBlur`, and `cv2.divide` functions. It accepts a file path as a command-line argument and writes the result with a `_sketch` suffix, demonstrating a straightforward image-processing pipeline.

TThomasG77
51% match
Loading thumbnail…

Gist 895545c65773a661a6035d5ebc9d1313

This notebook demonstrates a TensorFlow/Keras implementation of the Hausdorff distance metric, visualized with synthetic image data. It uses `skimage.draw.circle` to generate a ground-truth circle image, then computes and displays the Hausdorff distance between predicted and actual binary masks via matplotlib. The visualization includes an inline image plot of the mask, rendered as an interactive matplotlib axes image, alongside the execution of the metric computation within the Keras backend.

Aakeshavan
51% match
Loading thumbnail…

Gist 98636bb57280e38492740cdbe9c4901c

This example demonstrates a deep learning workflow for classifying brain images using TensorFlow and Keras. It loads CSV data from the braindr dataset, displaying a pandas DataFrame with vote counts, rater identities, and mean ratings for each image. The code builds a convolutional neural network with layers like Conv2D, MaxPooling2D, Dropout, and LeakyReLU, using Keras' Sequential API. It configures the model for GPU execution, imports optimizers such as RMSprop and Adam, and prepares callbacks like ModelCheckpoint for training.

Aakeshavan
51% match