alessiamarcolini

def clr(self):
        cycle = np.floor(1 + self.clr_iterations / (2 * self.step_size))
        x = np.abs(self.clr_iterations / self.step_size - 2 * cycle + 1)
        if self.scale_mode == 'cycle':
            return self.base_lr + (self.max_lr - self.base_lr) * \
                np.maximum(0, (1 - x)) * self.scale_fn(cycle)
        else:
            return self.base_lr + (self.max_lr - self.base_lr) * \
                np.maximum(0, (1 - x)) * self.scale_fn(self.clr_iterations)

alessiamarcolini

def step_decay(epoch):
    initial_lrate = 0.1
    drop = 0.5
    epochs_drop = 10.0
    lrate = initial_lrate * math.pow(drop, math.floor((1+epoch)/epochs_drop))
    return lrate
  
# ...
  
lrate = LearningRateScheduler(step_decay)

alessiamarcolini

# Compile model
epochs = 50
learning_rate = 0.1
decay_rate = learning_rate / epochs
momentum = 0.8
sgd = SGD(lr=learning_rate, momentum=momentum, decay=decay_rate, nesterov=False)
model.compile(loss='binary_crossentropy', optimizer=sgd, metrics=['accuracy'])

simonnanty

import tensorflow as tf

from tensorflow.python.ops import init_ops
from tensorflow.python.ops import array_ops
from tensorflow.python.ops import math_ops
from tensorflow.python.ops.rnn_cell_impl import RNNCell, _linear

class LRUCell(RNNCell): 
    """Lattice Recurrent Unit (LRU).
       This implementation is based on:

MartinThoma

import numpy as np
from keras import backend as K
from keras.models import Sequential
from keras.layers import Dense, Activation


def fro_norm(w):
    """Frobenius norm."""
    return K.sqrt(K.sum(K.square(K.abs(w))))

cbaziotis

def dot_product(x, kernel):
    """
    Wrapper for dot product operation, in order to be compatible with both
    Theano and Tensorflow
    Args:
        x (): input
        kernel (): weights
    Returns:
    """
    if K.backend() == 'tensorflow':

cbaziotis

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:

mbollmann

class AttentionLSTM(LSTM):
    """LSTM with attention mechanism

    This is an LSTM incorporating an attention mechanism into its hidden states.
    Currently, the context vector calculated from the attended vector is fed
    into the model's internal states, closely following the model by Xu et al.
    (2016, Sec. 3.1.2), using a soft attention model following
    Bahdanau et al. (2014).

    The layer expects two inputs instead of the usual one:

suziewong

1.同一台电脑可以有2个git账号（不同网站的）

首先不同网站，当然可以使用同一个邮箱，比如我的github，gitlab，bitbucket的账号都是monkeysuzie[at]gmail.com 这时候不用担心密钥的问题，因为这些网站push pull 认证的唯一性的是邮箱 比如我的windows 上 2个账号一个gitlab 一个github （用的都是id_rsa）

host github
  hostname github.com
  Port 22

host gitlab.zjut.com

agramfort

"""
Implementation of pairwise ranking using scikit-learn LinearSVC

Reference: "Large Margin Rank Boundaries for Ordinal Regression", R. Herbrich,
    T. Graepel, K. Obermayer.

Authors: Fabian Pedregosa <fabian@fseoane.net>
         Alexandre Gramfort <alexandre.gramfort@inria.fr>
"""