Gist 50acac748fdb4324a0dc2759fb6fce55

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.

75% match

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.

Convolutional Neural Networks

This example shows how convolutional neural networks (CNNs) classify images, using the MNIST dataset of handwritten digits. It presents the network architecture and training process in Keras, with code that defines convolutional and pooling layers via the Sequential API. The visualization demonstrates how filters extract features from input images, using Python’s TensorFlow and Keras libraries to run the model. It includes practical code snippets from tutorials, showing how to load data, build the CNN, and evaluate its accuracy, while referencing YouTube tutorials and source code repositories for further exploration.

Aaaizemberg

Gist 1ec7d82931c03d4134419af0ccfdd985

This visualization demonstrates a synthetic image-segmentation experiment using TensorFlow and Keras, where a binary mask of a filled circle is generated with the skimage.draw.circle function and displayed via matplotlib. The notebook focuses on computing the Hausdorff distance metric between predicted and ground-truth segmentation masks, using Keras backend operations to implement the distance calculation. The visualization shows the input circle image as a matplotlib axes image, illustrating how the metric is applied to evaluate segmentation quality. The code imports TensorFlow, NumPy, Keras backend, and matplotlib inline, establishing a workflow for comparing segmentation outputs against reference shapes.

Gist 1c87e6026e22589f1729

This visualization tracks the misclassification rate of a stochastic gradient descent classifier over 5,000 iterations, with separate lines for training and test datasets. The code uses Python with NumPy, Pandas, and Seaborn’s `color_palette` for styling, while Matplotlib’s `plot` and `legend` functions render the two curves. The y-axis shows misclassification rate and the x-axis shows iteration counter, revealing how the model’s performance evolves during a single pass through the data with a constant step size.

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.

63% match

Gist 2cfcfa50bdb3d72af8a3

This example demonstrates a complete neural network training pipeline for MNIST digit classification using Theano and the Blocks library. It constructs a two-layer MLP with rectified linear and softmax activations, applies L2 weight regularization, and trains the model via gradient descent with a scale step rule. The code uses Blocks' `ComputationGraph`, `VariableFilter`, and `DataStreamMonitoring` to track test cost, while Flatten transforms the MNIST data streams. Training runs for a single epoch with batch sizes of 256 and 1024 for training and testing, respectively.

SSamyMe

62% match

Gist b2f3fc64ccdc87810403f05a16159e6c

This notebook demonstrates a machine learning workflow for predicting reading outcomes from demographic and neuroimaging data. It loads a tab-separated dataset containing variables such as age, gender, cognitive scores, and a diffusion MRI measure (L_SLFp_FA), then builds and evaluates classification models using scikit-learn’s ExtraTreesClassifier and LogisticRegressionCV. The code employs a Pipeline with StandardScaler for preprocessing, and uses StratifiedKFold for cross-validation to assess model performance. Visualizations include a dataframe preview rendered as an HTML table via pandas, with the analysis executed in an inline matplotlib environment using seaborn for styling.