Skip to content

Instantly share code, notes, and snippets.

View alberduris's full-sized avatar
💪
Montando movidas

Alber alberduris

💪
Montando movidas
View GitHub Profile
@mblondel
mblondel / letor_metrics.py
Last active September 19, 2024 06:13
Learning to rank metrics.
# (C) Mathieu Blondel, November 2013
# License: BSD 3 clause
import numpy as np
def ranking_precision_score(y_true, y_score, k=10):
"""Precision at rank k
Parameters
@gabrieleangeletti
gabrieleangeletti / autoencoder.py
Last active October 15, 2019 15:16
Denoising Autoencoder implementation using TensorFlow.
import tensorflow as tf
import numpy as np
import os
import zconfig
import utils
class DenoisingAutoencoder(object):
""" Implementation of Denoising Autoencoders using TensorFlow.
@gabrieleangeletti
gabrieleangeletti / rbm_after_refactor.py
Last active July 27, 2021 14:32
Restricted Boltzmann Machine implementation in TensorFlow, before and after code refactoring. Blog post: http://blackecho.github.io/blog/programming/2016/02/21/refactoring-rbm-tensor-flow-implementation.html
import tensorflow as tf
import numpy as np
import os
import zconfig
import utils
class RBM(object):
@danijar
danijar / blog_tensorflow_variable_sequence_classification.py
Last active December 31, 2021 10:04
TensorFlow Variable-Length Sequence Classification
# Working example for my blog post at:
# http://danijar.com/variable-sequence-lengths-in-tensorflow/
import functools
import sets
import tensorflow as tf
from tensorflow.models.rnn import rnn_cell
from tensorflow.models.rnn import rnn
def lazy_property(function):
@cbaziotis
cbaziotis / Attention.py
Last active October 22, 2024 08:31
Keras Layer that implements an Attention mechanism for temporal data. Supports Masking. Follows the work of Raffel et al. [https://arxiv.org/abs/1512.08756]
from keras import backend as K, initializers, regularizers, constraints
from keras.engine.topology import Layer
def dot_product(x, kernel):
"""
Wrapper for dot product operation, in order to be compatible with both
Theano and Tensorflow
Args: