rnn.utils.py

import numpy as np

def softmax(x):
e_x = np.exp(x - np.max(x))
return e_x / e_x.sum(axis=0) def sigmoid(x):
return 1 / (1 + np.exp(-x))

引入所需的包

import numpy as np
from rnn_utils import *

1 - 基础循环神经网络的前向传播

下面是如何实现一个RNN:

Steps:

  1. 实现单步RNN所需的计算
  2. 循环

1.1 - RNN cell

def rnn_cell_forward(xt, a_prev, parameters):
"""
实现单步RNN Arguments:
xt -- your input data at timestep "t", numpy array of shape (n_x, m).
a_prev -- Hidden state at timestep "t-1", numpy array of shape (n_a, m)
parameters -- python dictionary containing:
Wax -- Weight matrix multiplying the input, numpy array of shape (n_a, n_x)
Waa -- Weight matrix multiplying the hidden state, numpy array of shape (n_a, n_a)
Wya -- Weight matrix relating the hidden-state to the output, numpy array of shape (n_y, n_a)
ba -- Bias, numpy array of shape (n_a, 1)
by -- Bias relating the hidden-state to the output, numpy array of shape (n_y, 1)
Returns:
a_next -- next hidden state, of shape (n_a, m)
yt_pred -- prediction at timestep "t", numpy array of shape (n_y, m)
cache -- tuple of values needed for the backward pass, contains (a_next, a_prev, xt, parameters)
""" # Retrieve parameters from "parameters"
Wax = parameters["Wax"]
Waa = parameters["Waa"]
Wya = parameters["Wya"]
ba = parameters["ba"]
by = parameters["by"] # compute next activation state using the formula given above
a_next = np.tanh(np.dot(Wax,xt) + np.dot(Waa,a_prev) + ba)
# compute output of the current cell using the formula given above
yt_pred = softmax(np.dot(Wya,a_next)+by) # store values you need for backward propagation in cache
cache = (a_next, a_prev, xt, parameters) return a_next, yt_pred, cache
np.random.seed(1)
xt = np.random.randn(3,10)
a_prev = np.random.randn(5,10)
Waa = np.random.randn(5,5)
Wax = np.random.randn(5,3)
Wya = np.random.randn(2,5)
ba = np.random.randn(5,1)
by = np.random.randn(2,1)
parameters = {"Waa": Waa, "Wax": Wax, "Wya": Wya, "ba": ba, "by": by} a_next, yt_pred, cache = rnn_cell_forward(xt, a_prev, parameters)
print("a_next[4] = ", a_next[4])
print("a_next.shape = ", a_next.shape)
print("yt_pred[1] =", yt_pred[1])
print("yt_pred.shape = ", yt_pred.shape)
a_next[4] =  [ 0.59584544  0.18141802  0.61311866  0.99808218  0.85016201  0.99980978
-0.18887155 0.99815551 0.6531151 0.82872037]
a_next.shape = (5, 10)
yt_pred[1] = [0.9888161 0.01682021 0.21140899 0.36817467 0.98988387 0.88945212
0.36920224 0.9966312 0.9982559 0.17746526]
yt_pred.shape = (2, 10)

1.2 - RNN 前向传播

def rnn_forward(x, a0, parameters):
"""
实现RNN前向传播 Arguments:
x -- Input data for every time-step, of shape (n_x, m, T_x).
a0 -- Initial hidden state, of shape (n_a, m)
parameters -- python dictionary containing:
Waa -- Weight matrix multiplying the hidden state, numpy array of shape (n_a, n_a)
Wax -- Weight matrix multiplying the input, numpy array of shape (n_a, n_x)
Wya -- Weight matrix relating the hidden-state to the output, numpy array of shape (n_y, n_a)
ba -- Bias numpy array of shape (n_a, 1)
by -- Bias relating the hidden-state to the output, numpy array of shape (n_y, 1) Returns:
a -- Hidden states for every time-step, numpy array of shape (n_a, m, T_x)
y_pred -- Predictions for every time-step, numpy array of shape (n_y, m, T_x)
caches -- tuple of values needed for the backward pass, contains (list of caches, x)
""" # Initialize "caches" which will contain the list of all caches
caches = [] # Retrieve dimensions from shapes of x and Wy
n_x, m, T_x = x.shape
n_y, n_a = parameters["Wya"].shape # initialize "a" and "y" with zeros
a = np.zeros((n_a,m,T_x))
y_pred = np.zeros((n_y,m,T_x)) # Initialize a_next
a_next = a0 # loop over all time-steps
for t in range(T_x):
# Update next hidden state, compute the prediction, get the cache
a_next, yt_pred, cache = rnn_cell_forward(x[:,:,t],a_next,parameters)
# Save the value of the new "next" hidden state in a
a[:,:,t] = a_next
# Save the value of the prediction in y
y_pred[:,:,t] = yt_pred
# Append "cache" to "caches"
caches.append(cache) # store values needed for backward propagation in cache
caches = (caches, x) return a, y_pred, caches
np.random.seed(1)
x = np.random.randn(3,10,4)
a0 = np.random.randn(5,10)
Waa = np.random.randn(5,5)
Wax = np.random.randn(5,3)
Wya = np.random.randn(2,5)
ba = np.random.randn(5,1)
by = np.random.randn(2,1)
parameters = {"Waa": Waa, "Wax": Wax, "Wya": Wya, "ba": ba, "by": by} a, y_pred, caches = rnn_forward(x, a0, parameters)
print("a[4][1] = ", a[4][1])
print("a.shape = ", a.shape)
print("y_pred[1][3] =", y_pred[1][3])
print("y_pred.shape = ", y_pred.shape)
print("caches[1][1][3] =", caches[1][1][3])
print("len(caches) = ", len(caches))
a[4][1] =  [-0.99999375  0.77911235 -0.99861469 -0.99833267]
a.shape = (5, 10, 4)
y_pred[1][3] = [0.79560373 0.86224861 0.11118257 0.81515947]
y_pred.shape = (2, 10, 4)
caches[1][1][3] = [-1.1425182 -0.34934272 -0.20889423 0.58662319]
len(caches) = 2

2 - 长短期记忆网络 LSTM

2.1 - LSTM cell

def lstm_cell_forward(xt, a_prev, c_prev, parameters):
"""
Implement a single forward step of the LSTM-cell as described in Figure (4) Arguments:
xt -- your input data at timestep "t", numpy array of shape (n_x, m).
a_prev -- Hidden state at timestep "t-1", numpy array of shape (n_a, m)
c_prev -- Memory state at timestep "t-1", numpy array of shape (n_a, m)
parameters -- python dictionary containing:
Wf -- Weight matrix of the forget gate, numpy array of shape (n_a, n_a + n_x)
bf -- Bias of the forget gate, numpy array of shape (n_a, 1)
Wi -- Weight matrix of the save gate, numpy array of shape (n_a, n_a + n_x)
bi -- Bias of the save gate, numpy array of shape (n_a, 1)
Wc -- Weight matrix of the first "tanh", numpy array of shape (n_a, n_a + n_x)
bc -- Bias of the first "tanh", numpy array of shape (n_a, 1)
Wo -- Weight matrix of the focus gate, numpy array of shape (n_a, n_a + n_x)
bo -- Bias of the focus gate, numpy array of shape (n_a, 1)
Wy -- Weight matrix relating the hidden-state to the output, numpy array of shape (n_y, n_a)
by -- Bias relating the hidden-state to the output, numpy array of shape (n_y, 1) Returns:
a_next -- next hidden state, of shape (n_a, m)
c_next -- next memory state, of shape (n_a, m)
yt_pred -- prediction at timestep "t", numpy array of shape (n_y, m)
cache -- tuple of values needed for the backward pass, contains (a_next, c_next, a_prev, c_prev, xt, parameters) Note: ft/it/ot stand for the forget/update/output gates, cct stands for the candidate value (c tilda),
c stands for the memory value
""" # 参数
Wf = parameters["Wf"]
bf = parameters["bf"]
Wi = parameters["Wi"]
bi = parameters["bi"]
Wc = parameters["Wc"]
bc = parameters["bc"]
Wo = parameters["Wo"]
bo = parameters["bo"]
Wy = parameters["Wy"]
by = parameters["by"] # 维度
n_x, m = xt.shape
n_y, n_a = Wy.shape # Concatenate a_prev and xt
concat = np.zeros((n_x + n_a,m))
concat[: n_a, :] = a_prev
concat[n_a :, :] = xt # 遗忘门
ft = sigmoid(np.dot(Wf,concat) + bf)
# 更新门
it = sigmoid(np.dot(Wi,concat) + bi)
# 记忆细胞的候选值
cct = np.tanh(np.dot(Wc,concat)+bc)
# 记忆细胞
c_next = ft*c_prev + it*cct
# 输出门
ot = sigmoid(np.dot(Wo,concat)+bo)
# a的输出
a_next = ot*np.tanh(c_next) # 预测值
yt_pred = softmax(np.dot(Wy, a_next) + by) # store values needed for backward propagation in cache
cache = (a_next, c_next, a_prev, c_prev, ft, it, cct, ot, xt, parameters) return a_next, c_next, yt_pred, cache
np.random.seed(1)
xt = np.random.randn(3,10)
a_prev = np.random.randn(5,10)
c_prev = np.random.randn(5,10)
Wf = np.random.randn(5, 5+3)
bf = np.random.randn(5,1)
Wi = np.random.randn(5, 5+3)
bi = np.random.randn(5,1)
Wo = np.random.randn(5, 5+3)
bo = np.random.randn(5,1)
Wc = np.random.randn(5, 5+3)
bc = np.random.randn(5,1)
Wy = np.random.randn(2,5)
by = np.random.randn(2,1) parameters = {"Wf": Wf, "Wi": Wi, "Wo": Wo, "Wc": Wc, "Wy": Wy, "bf": bf, "bi": bi, "bo": bo, "bc": bc, "by": by} a_next, c_next, yt, cache = lstm_cell_forward(xt, a_prev, c_prev, parameters)
print("a_next[4] = ", a_next[4])
print("a_next.shape = ", c_next.shape)
print("c_next[2] = ", c_next[2])
print("c_next.shape = ", c_next.shape)
print("yt[1] =", yt[1])
print("yt.shape = ", yt.shape)
print("cache[1][3] =", cache[1][3])
print("len(cache) = ", len(cache))
a_next[4] =  [-0.66408471  0.0036921   0.02088357  0.22834167 -0.85575339  0.00138482
0.76566531 0.34631421 -0.00215674 0.43827275]
a_next.shape = (5, 10)
c_next[2] = [ 0.63267805 1.00570849 0.35504474 0.20690913 -1.64566718 0.11832942
0.76449811 -0.0981561 -0.74348425 -0.26810932]
c_next.shape = (5, 10)
yt[1] = [0.79913913 0.15986619 0.22412122 0.15606108 0.97057211 0.31146381
0.00943007 0.12666353 0.39380172 0.07828381]
yt.shape = (2, 10)
cache[1][3] = [-0.16263996 1.03729328 0.72938082 -0.54101719 0.02752074 -0.30821874
0.07651101 -1.03752894 1.41219977 -0.37647422]
len(cache) = 10

2.2 - LSTM 前向传播

# GRADED FUNCTION: lstm_forward

def lstm_forward(x, a0, parameters):
"""
Implement the forward propagation of the recurrent neural network using an LSTM-cell described in Figure (3). Arguments:
x -- Input data for every time-step, of shape (n_x, m, T_x).
a0 -- Initial hidden state, of shape (n_a, m)
parameters -- python dictionary containing:
Wf -- Weight matrix of the forget gate, numpy array of shape (n_a, n_a + n_x)
bf -- Bias of the forget gate, numpy array of shape (n_a, 1)
Wi -- Weight matrix of the save gate, numpy array of shape (n_a, n_a + n_x)
bi -- Bias of the save gate, numpy array of shape (n_a, 1)
Wc -- Weight matrix of the first "tanh", numpy array of shape (n_a, n_a + n_x)
bc -- Bias of the first "tanh", numpy array of shape (n_a, 1)
Wo -- Weight matrix of the focus gate, numpy array of shape (n_a, n_a + n_x)
bo -- Bias of the focus gate, numpy array of shape (n_a, 1)
Wy -- Weight matrix relating the hidden-state to the output, numpy array of shape (n_y, n_a)
by -- Bias relating the hidden-state to the output, numpy array of shape (n_y, 1) Returns:
a -- Hidden states for every time-step, numpy array of shape (n_a, m, T_x)
y -- Predictions for every time-step, numpy array of shape (n_y, m, T_x)
caches -- tuple of values needed for the backward pass, contains (list of all the caches, x)
""" # Initialize "caches", which will track the list of all the caches
caches = [] ### START CODE HERE ###
# Retrieve dimensions from shapes of xt and Wy (≈2 lines)
n_x, m, T_x = x.shape
n_y, n_a = parameters['Wy'].shape # initialize "a", "c" and "y" with zeros (≈3 lines)
a = np.zeros((n_a, m, T_x))
c = np.zeros((n_a, m, T_x))
y = np.zeros((n_y, m, T_x)) # Initialize a_next and c_next (≈2 lines)
a_next = a0
c_next = np.zeros((n_a, m)) # loop over all time-steps
for t in range(T_x):
# Update next hidden state, next memory state, compute the prediction, get the cache (≈1 line)
a_next, c_next, yt, cache = lstm_cell_forward(x[:, :, t], a_next, c_next, parameters)
# Save the value of the new "next" hidden state in a (≈1 line)
a[:,:,t] = a_next
# Save the value of the prediction in y (≈1 line)
y[:,:,t] = yt
# Save the value of the next cell state (≈1 line)
c[:,:,t] = c_next
# Append the cache into caches (≈1 line)
caches.append(cache) ### END CODE HERE ### # store values needed for backward propagation in cache
caches = (caches, x) return a, y, c, caches
np.random.seed(1)
x = np.random.randn(3,10,7)
a0 = np.random.randn(5,10)
Wf = np.random.randn(5, 5+3)
bf = np.random.randn(5,1)
Wi = np.random.randn(5, 5+3)
bi = np.random.randn(5,1)
Wo = np.random.randn(5, 5+3)
bo = np.random.randn(5,1)
Wc = np.random.randn(5, 5+3)
bc = np.random.randn(5,1)
Wy = np.random.randn(2,5)
by = np.random.randn(2,1) parameters = {"Wf": Wf, "Wi": Wi, "Wo": Wo, "Wc": Wc, "Wy": Wy, "bf": bf, "bi": bi, "bo": bo, "bc": bc, "by": by} a, y, c, caches = lstm_forward(x, a0, parameters)
print("a[4][3][6] = ", a[4][3][6])
print("a.shape = ", a.shape)
print("y[1][4][3] =", y[1][4][3])
print("y.shape = ", y.shape)
print("caches[1][1[1]] =", caches[1][1][1])
print("c[1][2][1]", c[1][2][1])
print("len(caches) = ", len(caches))
a[4][3][6] =  0.17211776753291672
a.shape = (5, 10, 7)
y[1][4][3] = 0.9508734618501101
y.shape = (2, 10, 7)
caches[1][1[1]] = [ 0.82797464 0.23009474 0.76201118 -0.22232814 -0.20075807 0.18656139
0.41005165]
c[1][2][1] -0.8555449167181981
len(caches) = 2

3 - RNN反向传播

3.1 - 基础RNN反向传播

def rnn_cell_backward(da_next, cache):
"""
Implements the backward pass for the RNN-cell (single time-step). Arguments:
da_next -- Gradient of loss with respect to next hidden state
cache -- python dictionary containing useful values (output of rnn_step_forward()) Returns:
gradients -- python dictionary containing:
dx -- Gradients of input data, of shape (n_x, m)
da_prev -- Gradients of previous hidden state, of shape (n_a, m)
dWax -- Gradients of input-to-hidden weights, of shape (n_a, n_x)
dWaa -- Gradients of hidden-to-hidden weights, of shape (n_a, n_a)
dba -- Gradients of bias vector, of shape (n_a, 1)
""" # Retrieve values from cache
(a_next, a_prev, xt, parameters) = cache # Retrieve values from parameters
Wax = parameters["Wax"]
Waa = parameters["Waa"]
Wya = parameters["Wya"]
ba = parameters["ba"]
by = parameters["by"] # compute the gradient of tanh with respect to a_next
dtanh = (1-a_next*a_next)*da_next #注意这里是 element_wise ,即 * da_next,dtanh 可以只看做一个中间结果的表示方式 # compute the gradient of the loss with respect to Wax
dxt = np.dot(Wax.T, dtanh)
dWax = np.dot(dtanh,xt.T)
# 根据公式1、2, dxt = da_next .( Wax.T . (1- tanh(a_next)**2) ) = da_next .( Wax.T . dtanh * (1/d_a_next) )= Wax.T . dtanh
# 根据公式1、3, dWax = da_next .( (1- tanh(a_next)**2) . xt.T) = da_next .( dtanh * (1/d_a_next) . xt.T )= dtanh . xt.T
# 上面的 . 表示 np.dot # compute the gradient with respect to Waa
da_prev = np.dot(Waa.T, dtanh)
dWaa = np.dot( dtanh,a_prev.T) # compute the gradient with respect to b
dba = np.sum( dtanh,keepdims=True,axis=-1) # axis=0 列方向上操作 axis=1 行方向上操作 keepdims=True 矩阵的二维特性 # Store the gradients in a python dictionary
gradients = {"dxt": dxt, "da_prev": da_prev, "dWax": dWax, "dWaa": dWaa, "dba": dba} return gradients
np.random.seed(1)
xt = np.random.randn(3,10)
a_prev = np.random.randn(5,10)
Wax = np.random.randn(5,3)
Waa = np.random.randn(5,5)
Wya = np.random.randn(2,5)
b = np.random.randn(5,1)
by = np.random.randn(2,1)
parameters = {"Wax": Wax, "Waa": Waa, "Wya": Wya, "ba": ba, "by": by} a_next, yt, cache = rnn_cell_forward(xt, a_prev, parameters) da_next = np.random.randn(5,10)
gradients = rnn_cell_backward(da_next, cache)
print("gradients[\"dxt\"][1][2] =", gradients["dxt"][1][2])
print("gradients[\"dxt\"].shape =", gradients["dxt"].shape)
print("gradients[\"da_prev\"][2][3] =", gradients["da_prev"][2][3])
print("gradients[\"da_prev\"].shape =", gradients["da_prev"].shape)
print("gradients[\"dWax\"][3][1] =", gradients["dWax"][3][1])
print("gradients[\"dWax\"].shape =", gradients["dWax"].shape)
print("gradients[\"dWaa\"][1][2] =", gradients["dWaa"][1][2])
print("gradients[\"dWaa\"].shape =", gradients["dWaa"].shape)
print("gradients[\"dba\"][4] =", gradients["dba"][4])
print("gradients[\"dba\"].shape =", gradients["dba"].shape)
gradients["dxt"][1][2] = -0.4605641030588796
gradients["dxt"].shape = (3, 10)
gradients["da_prev"][2][3] = 0.08429686538067718
gradients["da_prev"].shape = (5, 10)
gradients["dWax"][3][1] = 0.3930818739219303
gradients["dWax"].shape = (5, 3)
gradients["dWaa"][1][2] = -0.2848395578696067
gradients["dWaa"].shape = (5, 5)
gradients["dba"][4] = [0.80517166]
gradients["dba"].shape = (5, 1)

通过RNN反向传播

def rnn_backward(da, caches):
"""
Implement the backward pass for a RNN over an entire sequence of input data. Arguments:
da -- Upstream gradients of all hidden states, of shape (n_a, m, T_x)
caches -- tuple containing information from the forward pass (rnn_forward) Returns:
gradients -- python dictionary containing:
dx -- Gradient w.r.t. the input data, numpy-array of shape (n_x, m, T_x)
da0 -- Gradient w.r.t the initial hidden state, numpy-array of shape (n_a, m)
dWax -- Gradient w.r.t the input's weight matrix, numpy-array of shape (n_a, n_x)
dWaa -- Gradient w.r.t the hidden state's weight matrix, numpy-arrayof shape (n_a, n_a)
dba -- Gradient w.r.t the bias, of shape (n_a, 1)
""" ### START CODE HERE ###
# Retrieve values from the first cache (t=1) of caches (≈2 lines)
(caches, x) = caches
(a1, a0, x1, parameters) = caches[0] # t=1 时的值 # Retrieve dimensions from da's and x1's shapes (≈2 lines)
n_a, m, T_x = da.shape
n_x, m = x1.shape # initialize the gradients with the right sizes (≈6 lines)
dx = np.zeros((n_x, m, T_x))
dWax = np.zeros((n_a, n_x))
dWaa = np.zeros((n_a, n_a))
dba = np.zeros((n_a, 1))
da0 = np.zeros((n_a, m))
da_prevt = np.zeros((n_a, m)) # Loop through all the time steps
for t in reversed(range(T_x)):
# Compute gradients at time step t. Choose wisely the "da_next" and the "cache" to use in the backward propagation step. (≈1 line)
gradients = rnn_cell_backward(da[:, :, t] + da_prevt, caches[t]) # da[:,:,t] + da_prevt ,每一个时间步后更新梯度
# Retrieve derivatives from gradients (≈ 1 line)
dxt, da_prevt, dWaxt, dWaat, dbat = gradients["dxt"], gradients["da_prev"], gradients["dWax"], gradients["dWaa"], gradients["dba"]
# Increment global derivatives w.r.t parameters by adding their derivative at time-step t (≈4 lines)
dx[:, :, t] = dxt
dWax += dWaxt
dWaa += dWaat
dba += dbat # Set da0 to the gradient of a which has been backpropagated through all time-steps (≈1 line)
da0 = da_prevt
### END CODE HERE ### # Store the gradients in a python dictionary
gradients = {"dx": dx, "da0": da0, "dWax": dWax, "dWaa": dWaa,"dba": dba} return gradients
np.random.seed(1)
x = np.random.randn(3,10,4)
a0 = np.random.randn(5,10)
Wax = np.random.randn(5,3)
Waa = np.random.randn(5,5)
Wya = np.random.randn(2,5)
ba = np.random.randn(5,1)
by = np.random.randn(2,1)
parameters = {"Wax": Wax, "Waa": Waa, "Wya": Wya, "ba": ba, "by": by}
a, y, caches = rnn_forward(x, a0, parameters)
da = np.random.randn(5, 10, 4)
gradients = rnn_backward(da, caches) print("gradients[\"dx\"][1][2] =", gradients["dx"][1][2])
print("gradients[\"dx\"].shape =", gradients["dx"].shape)
print("gradients[\"da0\"][2][3] =", gradients["da0"][2][3])
print("gradients[\"da0\"].shape =", gradients["da0"].shape)
print("gradients[\"dWax\"][3][1] =", gradients["dWax"][3][1])
print("gradients[\"dWax\"].shape =", gradients["dWax"].shape)
print("gradients[\"dWaa\"][1][2] =", gradients["dWaa"][1][2])
print("gradients[\"dWaa\"].shape =", gradients["dWaa"].shape)
print("gradients[\"dba\"][4] =", gradients["dba"][4])
print("gradients[\"dba\"].shape =", gradients["dba"].shape)
gradients["dx"][1][2] = [-2.07101689 -0.59255627  0.02466855  0.01483317]
gradients["dx"].shape = (3, 10, 4)
gradients["da0"][2][3] = -0.31494237512664996
gradients["da0"].shape = (5, 10)
gradients["dWax"][3][1] = 11.264104496527777
gradients["dWax"].shape = (5, 3)
gradients["dWaa"][1][2] = 2.303333126579893
gradients["dWaa"].shape = (5, 5)
gradients["dba"][4] = [-0.74747722]
gradients["dba"].shape = (5, 1)

3.2 - LSTM反向传播

3.2.1 单步反向传播

def lstm_cell_backward(da_next, dc_next, cache):
"""
Implement the backward pass for the LSTM-cell (single time-step). Arguments:
da_next -- Gradients of next hidden state, of shape (n_a, m)
dc_next -- Gradients of next cell state, of shape (n_a, m)
cache -- cache storing information from the forward pass Returns:
gradients -- python dictionary containing:
dxt -- Gradient of input data at time-step t, of shape (n_x, m)
da_prev -- Gradient w.r.t. the previous hidden state, numpy array of shape (n_a, m)
dc_prev -- Gradient w.r.t. the previous memory state, of shape (n_a, m, T_x)
dWf -- Gradient w.r.t. the weight matrix of the forget gate, numpy array of shape (n_a, n_a + n_x)
dWi -- Gradient w.r.t. the weight matrix of the input gate, numpy array of shape (n_a, n_a + n_x)
dWc -- Gradient w.r.t. the weight matrix of the memory gate, numpy array of shape (n_a, n_a + n_x)
dWo -- Gradient w.r.t. the weight matrix of the save gate, numpy array of shape (n_a, n_a + n_x)
dbf -- Gradient w.r.t. biases of the forget gate, of shape (n_a, 1)
dbi -- Gradient w.r.t. biases of the update gate, of shape (n_a, 1)
dbc -- Gradient w.r.t. biases of the memory gate, of shape (n_a, 1)
dbo -- Gradient w.r.t. biases of the save gate, of shape (n_a, 1)
""" # Retrieve information from "cache"
(a_next, c_next, a_prev, c_prev, ft, it, cct, ot, xt, parameters) = cache # Retrieve dimensions from xt's and a_next's shape (≈2 lines)
n_x, m = xt.shape
n_a, m = a_next.shape # Compute gates related derivatives, you can find their values can be found by looking carefully at equations (7) to (10) (≈4 lines)
dot = da_next * np.tanh(c_next) * ot * (1 - ot)
dcct = (dc_next * it + ot * (1 - np.square(np.tanh(c_next))) * it * da_next) * (1 - np.square(cct))
dit = (dc_next * cct + ot * (1 - np.square(np.tanh(c_next))) * cct * da_next) * it * (1 - it)
dft = (dc_next * c_prev + ot *(1 - np.square(np.tanh(c_next))) * c_prev * da_next) * ft * (1 - ft) # Code equations (7) to (10) (≈4 lines)
# dit = None
# dft = None
# dot = None
# dcct = None # Compute parameters related derivatives. Use equations (11)-(14) (≈8 lines)
dWf = np.dot(dft,np.concatenate((a_prev, xt), axis=0).T)
dWi = np.dot(dit,np.concatenate((a_prev, xt), axis=0).T)
dWc = np.dot(dcct,np.concatenate((a_prev, xt), axis=0).T)
dWo = np.dot(dot,np.concatenate((a_prev, xt), axis=0).T)
dbf = np.sum(dft, axis=1 ,keepdims = True)
dbi = np.sum(dit, axis=1, keepdims = True)
dbc = np.sum(dcct, axis=1, keepdims = True)
dbo = np.sum(dot, axis=1, keepdims = True) # Compute derivatives w.r.t previous hidden state, previous memory state and input. Use equations (15)-(17). (≈3 lines)
da_prev = np.dot(parameters['Wf'][:,:n_a].T,dft)+np.dot(parameters['Wi'][:,:n_a].T,dit)+np.dot(parameters['Wc'][:,:n_a].T,dcct)+np.dot(parameters['Wo'][:,:n_a].T,dot)
dc_prev = dc_next*ft+ot*(1-np.square(np.tanh(c_next)))*ft*da_next
dxt = np.dot(parameters['Wf'][:,n_a:].T,dft)+np.dot(parameters['Wi'][:,n_a:].T,dit)+np.dot(parameters['Wc'][:,n_a:].T,dcct)+np.dot(parameters['Wo'][:,n_a:].T,dot)
# parameters['Wf'][:, :n_a].T 每一行的 第 0 到 n_a-1 列的数据取出来
# parameters['Wf'][:, n_a:].T 每一行的 第 n_a 到最后列的数据取出来 # Save gradients in dictionary
gradients = {"dxt": dxt, "da_prev": da_prev, "dc_prev": dc_prev, "dWf": dWf,"dbf": dbf, "dWi": dWi,"dbi": dbi,
"dWc": dWc,"dbc": dbc, "dWo": dWo,"dbo": dbo} return gradients
np.random.seed(1)
xt = np.random.randn(3,10)
a_prev = np.random.randn(5,10)
c_prev = np.random.randn(5,10)
Wf = np.random.randn(5, 5+3)
bf = np.random.randn(5,1)
Wi = np.random.randn(5, 5+3)
bi = np.random.randn(5,1)
Wo = np.random.randn(5, 5+3)
bo = np.random.randn(5,1)
Wc = np.random.randn(5, 5+3)
bc = np.random.randn(5,1)
Wy = np.random.randn(2,5)
by = np.random.randn(2,1) parameters = {"Wf": Wf, "Wi": Wi, "Wo": Wo, "Wc": Wc, "Wy": Wy, "bf": bf, "bi": bi, "bo": bo, "bc": bc, "by": by} a_next, c_next, yt, cache = lstm_cell_forward(xt, a_prev, c_prev, parameters) da_next = np.random.randn(5,10)
dc_next = np.random.randn(5,10)
gradients = lstm_cell_backward(da_next, dc_next, cache)
print("gradients[\"dxt\"][1][2] =", gradients["dxt"][1][2])
print("gradients[\"dxt\"].shape =", gradients["dxt"].shape)
print("gradients[\"da_prev\"][2][3] =", gradients["da_prev"][2][3])
print("gradients[\"da_prev\"].shape =", gradients["da_prev"].shape)
print("gradients[\"dc_prev\"][2][3] =", gradients["dc_prev"][2][3])
print("gradients[\"dc_prev\"].shape =", gradients["dc_prev"].shape)
print("gradients[\"dWf\"][3][1] =", gradients["dWf"][3][1])
print("gradients[\"dWf\"].shape =", gradients["dWf"].shape)
print("gradients[\"dWi\"][1][2] =", gradients["dWi"][1][2])
print("gradients[\"dWi\"].shape =", gradients["dWi"].shape)
print("gradients[\"dWc\"][3][1] =", gradients["dWc"][3][1])
print("gradients[\"dWc\"].shape =", gradients["dWc"].shape)
print("gradients[\"dWo\"][1][2] =", gradients["dWo"][1][2])
print("gradients[\"dWo\"].shape =", gradients["dWo"].shape)
print("gradients[\"dbf\"][4] =", gradients["dbf"][4])
print("gradients[\"dbf\"].shape =", gradients["dbf"].shape)
print("gradients[\"dbi\"][4] =", gradients["dbi"][4])
print("gradients[\"dbi\"].shape =", gradients["dbi"].shape)
print("gradients[\"dbc\"][4] =", gradients["dbc"][4])
print("gradients[\"dbc\"].shape =", gradients["dbc"].shape)
print("gradients[\"dbo\"][4] =", gradients["dbo"][4])
print("gradients[\"dbo\"].shape =", gradients["dbo"].shape)
gradients["dxt"][1][2] = 3.2305591151091884
gradients["dxt"].shape = (3, 10)
gradients["da_prev"][2][3] = -0.06396214197109241
gradients["da_prev"].shape = (5, 10)
gradients["dc_prev"][2][3] = 0.7975220387970015
gradients["dc_prev"].shape = (5, 10)
gradients["dWf"][3][1] = -0.1479548381644968
gradients["dWf"].shape = (5, 8)
gradients["dWi"][1][2] = 1.0574980552259903
gradients["dWi"].shape = (5, 8)
gradients["dWc"][3][1] = 2.3045621636876668
gradients["dWc"].shape = (5, 8)
gradients["dWo"][1][2] = 0.3313115952892109
gradients["dWo"].shape = (5, 8)
gradients["dbf"][4] = [0.18864637]
gradients["dbf"].shape = (5, 1)
gradients["dbi"][4] = [-0.40142491]
gradients["dbi"].shape = (5, 1)
gradients["dbc"][4] = [0.25587763]
gradients["dbc"].shape = (5, 1)
gradients["dbo"][4] = [0.13893342]
gradients["dbo"].shape = (5, 1)

3.3 通过RNN和LSTM反向传播

def lstm_backward(da, caches):

    """
Implement the backward pass for the RNN with LSTM-cell (over a whole sequence). Arguments:
da -- Gradients w.r.t the hidden states, numpy-array of shape (n_a, m, T_x)
dc -- Gradients w.r.t the memory states, numpy-array of shape (n_a, m, T_x)
caches -- cache storing information from the forward pass (lstm_forward) Returns:
gradients -- python dictionary containing:
dx -- Gradient of inputs, of shape (n_x, m, T_x)
da0 -- Gradient w.r.t. the previous hidden state, numpy array of shape (n_a, m)
dWf -- Gradient w.r.t. the weight matrix of the forget gate, numpy array of shape (n_a, n_a + n_x)
dWi -- Gradient w.r.t. the weight matrix of the update gate, numpy array of shape (n_a, n_a + n_x)
dWc -- Gradient w.r.t. the weight matrix of the memory gate, numpy array of shape (n_a, n_a + n_x)
dWo -- Gradient w.r.t. the weight matrix of the save gate, numpy array of shape (n_a, n_a + n_x)
dbf -- Gradient w.r.t. biases of the forget gate, of shape (n_a, 1)
dbi -- Gradient w.r.t. biases of the update gate, of shape (n_a, 1)
dbc -- Gradient w.r.t. biases of the memory gate, of shape (n_a, 1)
dbo -- Gradient w.r.t. biases of the save gate, of shape (n_a, 1)
""" # Retrieve values from the first cache (t=1) of caches.
(caches, x) = caches
(a1, c1, a0, c0, f1, i1, cc1, o1, x1, parameters) = caches[0] # Retrieve dimensions from da's and x1's shapes (≈2 lines)
n_a, m, T_x = da.shape
n_x, m = x1.shape # initialize the gradients with the right sizes (≈12 lines)
dx = np.zeros((n_x, m, T_x))
da0 = np.zeros((n_a, m))
da_prevt = np.zeros((n_a, m))
dc_prevt = np.zeros((n_a, m))
dWf = np.zeros((n_a, n_a + n_x))
dWi = np.zeros((n_a, n_a + n_x))
dWc = np.zeros((n_a, n_a + n_x))
dWo = np.zeros((n_a, n_a + n_x))
dbf = np.zeros((n_a, 1))
dbi = np.zeros((n_a, 1))
dbc = np.zeros((n_a, 1))
dbo = np.zeros((n_a, 1)) # loop back over the whole sequence
for t in reversed(range(T_x)):
# Compute all gradients using lstm_cell_backward
gradients = lstm_cell_backward(da[:,:,t]+da_prevt,dc_prevt,caches[t])
# Store or add the gradient to the parameters' previous step's gradient
dx[:, :, t] = gradients['dxt']
dWf = dWf+gradients['dWf']
dWi = dWi+gradients['dWi']
dWc = dWc+gradients['dWc']
dWo = dWo+gradients['dWo']
dbf = dbf+gradients['dbf']
dbi = dbi+gradients['dbi']
dbc = dbc+gradients['dbc']
dbo = dbo+gradients['dbo']
# Set the first activation's gradient to the backpropagated gradient da_prev.
da0 = gradients['da_prev'] # Store the gradients in a python dictionary
gradients = {"dx": dx, "da0": da0, "dWf": dWf,"dbf": dbf, "dWi": dWi,"dbi": dbi,
"dWc": dWc,"dbc": dbc, "dWo": dWo,"dbo": dbo} return gradients
np.random.seed(1)
x = np.random.randn(3,10,7)
a0 = np.random.randn(5,10)
Wf = np.random.randn(5, 5+3)
bf = np.random.randn(5,1)
Wi = np.random.randn(5, 5+3)
bi = np.random.randn(5,1)
Wo = np.random.randn(5, 5+3)
bo = np.random.randn(5,1)
Wc = np.random.randn(5, 5+3)
bc = np.random.randn(5,1) parameters = {"Wf": Wf, "Wi": Wi, "Wo": Wo, "Wc": Wc, "Wy": Wy, "bf": bf, "bi": bi, "bo": bo, "bc": bc, "by": by} a, y, c, caches = lstm_forward(x, a0, parameters) da = np.random.randn(5, 10, 4)
gradients = lstm_backward(da, caches) print("gradients[\"dx\"][1][2] =", gradients["dx"][1][2])
print("gradients[\"dx\"].shape =", gradients["dx"].shape)
print("gradients[\"da0\"][2][3] =", gradients["da0"][2][3])
print("gradients[\"da0\"].shape =", gradients["da0"].shape)
print("gradients[\"dWf\"][3][1] =", gradients["dWf"][3][1])
print("gradients[\"dWf\"].shape =", gradients["dWf"].shape)
print("gradients[\"dWi\"][1][2] =", gradients["dWi"][1][2])
print("gradients[\"dWi\"].shape =", gradients["dWi"].shape)
print("gradients[\"dWc\"][3][1] =", gradients["dWc"][3][1])
print("gradients[\"dWc\"].shape =", gradients["dWc"].shape)
print("gradients[\"dWo\"][1][2] =", gradients["dWo"][1][2])
print("gradients[\"dWo\"].shape =", gradients["dWo"].shape)
print("gradients[\"dbf\"][4] =", gradients["dbf"][4])
print("gradients[\"dbf\"].shape =", gradients["dbf"].shape)
print("gradients[\"dbi\"][4] =", gradients["dbi"][4])
print("gradients[\"dbi\"].shape =", gradients["dbi"].shape)
print("gradients[\"dbc\"][4] =", gradients["dbc"][4])
print("gradients[\"dbc\"].shape =", gradients["dbc"].shape)
print("gradients[\"dbo\"][4] =", gradients["dbo"][4])
print("gradients[\"dbo\"].shape =", gradients["dbo"].shape)
gradients["dx"][1][2] = [-0.00173313  0.08287442 -0.30545663 -0.43281115]
gradients["dx"].shape = (3, 10, 4)
gradients["da0"][2][3] = -0.09591150195400465
gradients["da0"].shape = (5, 10)
gradients["dWf"][3][1] = -0.06981985612744009
gradients["dWf"].shape = (5, 8)
gradients["dWi"][1][2] = 0.10237182024854771
gradients["dWi"].shape = (5, 8)
gradients["dWc"][3][1] = -0.062498379492745226
gradients["dWc"].shape = (5, 8)
gradients["dWo"][1][2] = 0.04843891314443013
gradients["dWo"].shape = (5, 8)
gradients["dbf"][4] = [-0.0565788]
gradients["dbf"].shape = (5, 1)
gradients["dbi"][4] = [-0.15399065]
gradients["dbi"].shape = (5, 1)
gradients["dbc"][4] = [-0.29691142]
gradients["dbc"].shape = (5, 1)
gradients["dbo"][4] = [-0.29798344]
gradients["dbo"].shape = (5, 1)

逐步构建循环神经网络 RNN的更多相关文章

  1. 循环神经网络RNN模型和长短时记忆系统LSTM

    传统DNN或者CNN无法对时间序列上的变化进行建模,即当前的预测只跟当前的输入样本相关,无法建立在时间或者先后顺序上出现在当前样本之前或者之后的样本之间的联系.实际的很多场景中,样本出现的时间顺序非常 ...

  2. 用纯Python实现循环神经网络RNN向前传播过程(吴恩达DeepLearning.ai作业)

    Google TensorFlow程序员点赞的文章!   前言 目录: - 向量表示以及它的维度 - rnn cell - rnn 向前传播 重点关注: - 如何把数据向量化的,它们的维度是怎么来的 ...

  3. 循环神经网络(RNN, Recurrent Neural Networks)介绍(转载)

    循环神经网络(RNN, Recurrent Neural Networks)介绍    这篇文章很多内容是参考:http://www.wildml.com/2015/09/recurrent-neur ...

  4. 通过keras例子理解LSTM 循环神经网络(RNN)

    博文的翻译和实践: Understanding Stateful LSTM Recurrent Neural Networks in Python with Keras 正文 一个强大而流行的循环神经 ...

  5. 循环神经网络RNN及LSTM

    一.循环神经网络RNN RNN综述 https://juejin.im/entry/5b97e36cf265da0aa81be239 RNN中为什么要采用tanh而不是ReLu作为激活函数?  htt ...

  6. 深度学习之循环神经网络RNN概述,双向LSTM实现字符识别

    深度学习之循环神经网络RNN概述,双向LSTM实现字符识别 2. RNN概述 Recurrent Neural Network - 循环神经网络,最早出现在20世纪80年代,主要是用于时序数据的预测和 ...

  7. 从网络架构方面简析循环神经网络RNN

    一.前言 1.1 诞生原因 在普通的前馈神经网络(如多层感知机MLP,卷积神经网络CNN)中,每次的输入都是独立的,即网络的输出依赖且仅依赖于当前输入,与过去一段时间内网络的输出无关.但是在现实生活中 ...

  8. 循环神经网络(RNN, Recurrent Neural Networks)介绍

    原文地址: http://blog.csdn.net/heyongluoyao8/article/details/48636251# 循环神经网络(RNN, Recurrent Neural Netw ...

  9. 『cs231n』循环神经网络RNN

    循环神经网络 循环神经网络介绍摘抄自莫凡博士的教程 序列数据 我们想象现在有一组序列数据 data 0,1,2,3. 在当预测 result0 的时候,我们基于的是 data0, 同样在预测其他数据的 ...

随机推荐

  1. IFrame标签的两个用法介绍

    1. 作为弹出层铺底覆盖 大家如果做过那种黑色遮罩盖住整张页面,而碰巧用户用的是IE6,更碰巧的是页面上有select元素,那就有得头疼了(原理就不在这里赘述了).我们会发现弹出的DIV没法遮住sel ...

  2. F#周报2019年第5期

    新闻 Ionide的Open Collective 发布SAFE至Google Cloud Kubernetes引擎 .NET Core 3预览2 ASP.NET Core在.NET Core 3预览 ...

  3. How to enable Linux-PAM on uClinux

    By default the uClinux  uses the tools provided by busybox firstly. So the init login and passwd are ...

  4. [特征工程]-------使用sklearn做单机特征工程[转载]

    https://www.cnblogs.com/jasonfreak/p/5448385.html 使用sklearn做单机特征工程 目录 1 特征工程是什么?2 数据预处理 2.1 无量纲化 2.1 ...

  5. windows 创建共享文件夹

    1.右键要共享的文件夹----“共享”------“指定特定用户”,出现如下对话框: 2.选择“Everyone”,点击“共享”按钮,如下: 3.打开“运行“(win+r),输入上图 双反斜杠后面的内 ...

  6. 17.3-uC/OS-III消息管理(消息队列使用)

    多值信号量和和互斥信号量主要用来标志事件是否发生和协调资源的访问.如果要给资源赋予内容进行传递, 信号量就力有所不及了.这时候就需要用到 uC/OS 操作系统的另一个内核机制了,那就是消息队列. 2. ...

  7. https SSL主流数字证书都有哪些格式(转载)

    主流数字证书都有哪些格式? 一般来说,主流的Web服务软件,通常都基于两种基础密码库:OpenSSL和Java. Tomcat.Weblogic.JBoss等,使用Java提供的密码库.通过Java的 ...

  8. abap 断言

    1: Assert equal http://www.saptechnical.com/Tutorials/OOPS/ABAPUnit/Index.htm

  9. 六、APP开发的主角——UIViewController

    MVC框架模式 MVC即model(模型).view(视图)和controller(控制器)的缩写,是一种软件设计模式,专用于含有图形化用户界面的软件设计,自20世纪80年代以来已经有30多年的历史了 ...

  10. Mybatis入门及于hibernate的区别

    pojo:不按mvc分层,只是java bean有一些属性,还有get set方法domain:不按mvc分层,只是java bean有一些属性,还有get set方法po:用在持久层,还可以再增加或 ...