0
这是我收到的错误： mtrand.RandomState.randint中的文件“mtrand.pyx”，行1192 numpy/random/mtrand/mtrand.c：14128）Theano ANN“TypeError：randint（）至少需要1个位置参数（给出0）”
我对编码有点新，但我真的想从简单的ANN开始，所以我决定开始这个项目。
类型错误：randint（）采用（给出0）至少1位置参数
＃ - - 编码：UTF-8 - - “”” 创建于太阳09月18十四时56分44秒2016
@author: Jamoonie
"""
##theano practice
import numpy as np
import theano
import theano.tensor as T
from sklearn.datasets import load_digits
digits=load_digits()
print (digits.data.shape)
train_x = list(digits.data)
#print train_x.count
train_x = np.array(train_x)
#print train_x
train_y = list(digits.target)
#print train_y.count
train_y = np.array(train_y)
#print train_y
#q = T.matrix('q') checking how matrix dot products work, and how the row,col of the W0 should be set up
#q = np.zeros([5,10])
#print q
#p = T.matrix('p')
#p = np.zeros([10,5])
#
#print np.dot(q,p)
nn_input_dim = train_x.shape[1] ## if shape[0] it yields 1797, which is the number of rows
print nn_input_dim ##shows 64; shape[1] yields 1 row thus 64 columns! which are the layers of data we want to apply
nn_hdim0 = 10
nn_output_dim = len(train_y)
#nn_hdim0 = np.transpose(np.zeros(digits.data.shape))
#print nn_hdim0
epsilon = 0.008
batch_size = 100 ## how much data input per iteration
X = T.matrix('X')
y = T.lvector('y')
## set weight shapeswith random values
#W0 = np.transpose(np.zeros(digits.data.shape))
W0 = theano.shared(np.random.randn(nn_input_dim,nn_hdim0),name='W0') ##the shape of W0 should be row=input_dim, col=# hidden nodes
b0 = theano.shared(np.zeros(nn_hdim0),name='b0')
W1 = theano.shared(np.random.randn(nn_hdim0,nn_output_dim),name='W1') ## shape of W1 should have row=#hidden nodes, col = output dimension
b1 = theano.shared(np.zeros(nn_output_dim),name='b1')
z0 = X.dot(W0)+b0
a0 = T.nnet.softmax(z0) ## first hidden layer result
z1 = a0.dot(W1)+b1
a1 = T.nnet.softmax(z1) ## final result or prediction
loss = T.nnet.categorical_crossentropy(a1,y).mean() ## howmuch the prediction differrs from the real result
prediction = T.argmax(a1,axis=1) ## the maximum values of a1, presented in index posn 1
fwd_propagation = theano.function([X],a1) ## forward propagation function dpeneding on the array of X values and final prediction
calc_loss = theano.function([X,y],loss)
predict= theano.function([X],prediction)
accuracy = theano.function([X],T.sum(T.eq(prediction,train_y))) ## T.eq is elementwise. so this does an elementwise sum of prediction and train_y
dW0 = T.grad(loss,W0)
dW1 = T.grad(loss,W1)
db0=T.grad(loss,b0)
db1=T.grad(loss,b1)
np.random.randint()
gradient_step = theano.function(
[X,y], ##for each set of X,y values
updates=((W1,W1-epsilon*dW1), ##updates W1 by deltaW1(error)*learning rate and subtracting from original W1
(W0,W0-epsilon*dW0),
(b1,b1-epsilon*db1),
(b0,b0-epsilon*db0)))
def build(iterations = 80000):
W1.set_value(np.random.randn(nn_hdim0,nn_output_dim)/np.sqrt(nn_input_dim)) ## why dividing by the sqrt of nn_input_dim,i'm not sure, but they're meant to be random anyway.
W0.set_value(np.random.randn(nn_input_dim,nn_hdim0)/np.sqrt(nn_input_dim))
b1.set_value(np.zeros(nn_output_dim))
b0.set_value(np.zeros(nn_hdim0))
for i in range(0, iterations):
batch_indicies=np.random.randint(0,17,size=100)
batch_x,batch_y=train_x[batch_indicies],train_y[batch_indicies]
gradient_step(batch_x,batch_y)
##so we're providing the values now for the weights, biases and input output values
if i%2000==0:
print("loss after iteration %r: %r" % (i, calc_loss(train_x,train_y)))
print(accuracy(train_x))
if i==80000:
print (W0,b0,W1,b1)
build()