Skip to content

Instantly share code, notes, and snippets.

View Sklavit's full-sized avatar

Sergii Nechuiviter Sklavit

View GitHub Profile
@Sklavit
Sklavit / AttentionWithContext.py
Created April 26, 2017 09:43 — forked from cbaziotis/AttentionWithContext.py
Keras Layer that implements an Attention mechanism, with a context/query vector, for temporal data. Supports Masking. Follows the work of Yang et al. [https://www.cs.cmu.edu/~diyiy/docs/naacl16.pdf] "Hierarchical Attention Networks for Document Classification"
class AttentionWithContext(Layer):
"""
Attention operation, with a context/query vector, for temporal data.
Supports Masking.
Follows the work of Yang et al. [https://www.cs.cmu.edu/~diyiy/docs/naacl16.pdf]
"Hierarchical Attention Networks for Document Classification"
by using a context vector to assist the attention
# Input shape
3D tensor with shape: `(samples, steps, features)`.
# Output shape
@Sklavit
Sklavit / colorized_voronoi_with_clipping.py
Created March 26, 2017 00:36 — forked from pv/colorized_voronoi.py
Colorized Voronoi diagram with Scipy, in 2D, including infinite regions which are clipped to given box.
# coding=utf-8
import numpy as np
import matplotlib.pyplot as plt
from scipy.spatial import Voronoi
from shapely.geometry import Polygon
def voronoi_finite_polygons_2d(vor, radius=None):
"""
Reconstruct infinite voronoi regions in a 2D diagram to finite
regions.