MissHanJ

@MissHanJ·2 public vizzes

D3: Scatterplot!

This interactive scatterplot displays 50 random data points on Cartesian axes, with each circle colored blue or red depending on whether its x-coordinate falls in the left or right half of the plot. Clicking the “Randomize” button generates a fresh dataset and smoothly animates the points, axes, and color updates over two seconds. The visualization is built with D3 3.5.5, using the `d3.scale.linear`, `d3.svg.axis`, and `transition().duration(2000)` APIs, and renders entirely as SVG. The code derives from Scott Murray’s examples, forked from earlier gists by anonymous and jalapic.

Sep 13, 2016

Loading thumbnail…

TensorFlow Variable-Length Sequence Labelling

This example demonstrates a TensorFlow recurrent neural network that labels variable-length sequences, using GRU cells to process input data and a softmax layer to classify each time step. It defines a `VariableSequenceLabelling` class with lazy properties for prediction, cost, and error, and relies on TensorFlow’s `dynamic_rnn`, `rnn_cell.GRUCell`, and Adam optimizer. The model is trained and evaluated on an OCR dataset from the `sets` library, reshaping flattened images and using one-hot encoded targets, with training and test splits provided by `sets.Split`.

Jun 2, 2016