Skip to content

Instantly share code, notes, and snippets.

View SumiHui's full-sized avatar

SumiHui SumiHui

14 followers · 12 following
View GitHub Profile
@SumiHui
SumiHui / contextual_loss.py
Created August 23, 2019 10:23 — forked from yunjey/contextual_loss.py
pytorch implementation of contextual loss: https://arxiv.org/abs/1803.02077
def contextual_loss(x, y, h=0.5):
"""Computes contextual loss between x and y.
Args:
x: features of shape (N, C, H, W).
y: features of shape (N, C, H, W).
Returns:
cx_loss = contextual loss between x and y (Eq (1) in the paper)
"""
@SumiHui
SumiHui / blog_tensorflow_variable_sequence_labelling.py
Created June 15, 2018 09:22 — forked from danijar/blog_tensorflow_variable_sequence_labelling.py
TensorFlow Variable-Length Sequence Labelling
# 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):
@SumiHui
SumiHui / blog_tensorflow_sequence_classification.py
Created June 15, 2018 09:21 — forked from danijar/blog_tensorflow_sequence_classification.py
TensorFlow Sequence Classification
# Example for my blog post at:
# https://danijar.com/introduction-to-recurrent-networks-in-tensorflow/
import functools
import sets
import tensorflow as tf
def lazy_property(function):
attribute = '_' + function.__name__