Tensorflow 多分类问题

import requests
import numpy as np
复制代码

r = requests.get('http://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data')
复制代码

with open('iris.data', 'w') as f:
    f.write(r.text)
复制代码

import pandas as pd

复制代码

data = pd.read_csv('iris.data', names =['e_cd', 'e_kd', 'b_cd', 'b_kd', 'cat'])
复制代码

data.head(5)
复制代码

	e_cd	e_kd	b_cd	b_kd	cat
0	5.1	3.5	1.4	0.2	Iris-setosa
1	4.9	3.0	1.4	0.2	Iris-setosa
2	4.7	3.2	1.3	0.2	Iris-setosa
3	4.6	3.1	1.5	0.2	Iris-setosa
4	5.0	3.6	1.4	0.2	Iris-setosa

data.cat.unique()
复制代码

array(['Iris-setosa', 'Iris-versicolor', 'Iris-virginica'], dtype=object)
复制代码

data['c1'] = np.array(data['cat'] == 'Iris-setosa').astype(np.float32)
data['c2'] = np.array(data['cat'] == 'Iris-versicolor').astype(np.float32)
data['c3'] = np.array(data['cat'] == 'Iris-virginica').astype(np.float32)
复制代码

target = np.stack([data.c1.values, data.c2.values, data.c3.values]).T
复制代码

shuju = np.stack([data.e_cd.values, data.e_kd.values, data.b_cd.values, data.b_kd.values]).T
复制代码

np.shape(shuju), np.shape(target)
复制代码

((150, 4), (150, 3))
复制代码

import tensorflow as tf
复制代码

/anaconda3/envs/py35/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: compiletime version 3.6 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.5
  return f(*args, **kwds)
/anaconda3/envs/py35/lib/python3.5/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
  from ._conv import register_converters as _register_converters
复制代码

x = tf.placeholder("float", shape=[None, 4])
y = tf.placeholder("float", shape=[None, 3])
复制代码

weight = tf.Variable(tf.truncated_normal([4,3]))
bias = tf.Variable(tf.truncated_normal([3]))
复制代码

combine_input = tf.matmul(x, weight) + bias
复制代码

pred = tf.nn.softmax(combine_input)
复制代码

y.get_shape(), pred.get_shape()
复制代码

(TensorShape([Dimension(None), Dimension(3)]),
 TensorShape([Dimension(None), Dimension(3)]))
复制代码

loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=combine_input))
复制代码

WARNING:tensorflow:From <ipython-input-18-6b11325178b9>:1: softmax_cross_entropy_with_logits (from tensorflow.python.ops.nn_ops) is deprecated and will be removed in a future version.
Instructions for updating:

Future major versions of TensorFlow will allow gradients to flow
into the labels input on backprop by default.

See tf.nn.softmax_cross_entropy_with_logits_v2.
复制代码

correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
复制代码

train_step = tf.train.AdamOptimizer(0.0005).minimize(loss)
复制代码

sess = tf.Session()
sess.run(tf.global_variables_initializer())
复制代码

for i in range(10000):
    index = np.random.permutation(len(target))
    shuju =shuju[index]
    target = target[index]
    sess.run(train_step, feed_dict={x:shuju, y:target})
    if i%1000 == 0:
        print(sess.run((loss, accuracy), feed_dict={x:shuju, y:target}))
复制代码

(0.48896936, 0.74)
(0.3105031, 0.91333336)
(0.23715515, 0.9533333)
(0.18639529, 0.96666664)
(0.15062416, 0.96666664)
(0.12501644, 0.98)
(0.10630642, 0.98)
(0.09238311, 0.98)
(0.08186688, 0.98)
(0.07382768, 0.98)
复制代码

print(sess.run(weight))
复制代码

[[ 1.319767    1.5383282  -1.6495701 ]
 [ 4.432047    0.22605467 -3.0211918 ]
 [-4.785147   -1.7326641   3.8946218 ]
 [-4.521448   -2.30758     3.069917  ]]
复制代码

print(sess.run(bias))
复制代码

[ 1.521937  2.874068 -4.503109]
复制代码