张量流,预测值概率(ROI)

时间:2017-07-24 12:32:50

标签: python tensorflow predict roi

我遇到了同样的问题,Tensorflow, probability of predicted value?但是我使用了预测2,而且我不知道如何打印预测的百分比(置信度)。我的问题是,我可以重用你的代码(或部分代码)吗?或者如何使用pedict_proba? (我是python中的新手,我需要大力帮助)。那是我的代码:

(MAIN) This one activate the predict 2 :

import os
import sys
import predict_2
import glob
import numpy as np
import subprocess
from subprocess import call
from dask.dataframe.tests.test_rolling import idx
from sympy.tensor.indexed import Idx
import shutil
import tensorflow as tf
import keras.models
from keras.models import Sequential
from dask.array.learn import predict

x = [i[2] for i in os.walk('C:\\Users\\bob\\Desktop\\Bonifici\\Files\\num\\')]
y=[]
for t in x:
    for f in t:
        y.append(f)

path = ('C:\\Users\\bob\\Desktop\\Bonifici\\Files\\num\\')

i=0
idx = 0
nlist = []
for i in y:
    test = subprocess.check_output('python predict_2.py ' + path + str(y[idx]),shell=True).strip()
    idx+=1
    print(test)
    nlist.append(test)
print(nlist)

# unisce i file txt
idx=0

with open('C:\\Users\\bob\\Desktop\\bonifici\\Files\\CAUSALE.txt', "wb") as outfile:
    for f in nlist:
        outfile.write(nlist[idx])
        idx+=1



outfile.close()








This is the predict:

    # import modules
import sys
import tensorflow as tf
from PIL import Image, ImageFilter
from PIL import Image as PImage
import os
from os import listdir
import warnings
import math

#TOGLIE WARNING INERENTI ALLA CPU
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'

def predictint(imvalue):

    # Define the model (same as when creating the model file)
    x = tf.placeholder(tf.float32, [None, 784])
    W = tf.Variable(tf.zeros([784, 10]))
    b = tf.Variable(tf.zeros([10]))

    def weight_variable(shape):
        initial = tf.truncated_normal(shape, stddev=0.1)
        return tf.Variable(initial)

    def bias_variable(shape):
        initial = tf.constant(0.1, shape=shape)
        return tf.Variable(initial)

    def conv2d(x, W):
        return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

    def max_pool_2x2(x):
        return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')

    W_conv1 = weight_variable([5, 5, 1, 32])
    b_conv1 = bias_variable([32])

    x_image = tf.reshape(x, [-1, 28, 28, 1])
    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
    h_pool1 = max_pool_2x2(h_conv1)

    W_conv2 = weight_variable([5, 5, 32, 64])
    b_conv2 = bias_variable([64])

    h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
    h_pool2 = max_pool_2x2(h_conv2)

    W_fc1 = weight_variable([7 * 7 * 64, 1024])
    b_fc1 = bias_variable([1024])

    h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

    keep_prob = tf.placeholder(tf.float32)
    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

    W_fc2 = weight_variable([1024, 10])
    b_fc2 = bias_variable([10])

    y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

    init_op = tf.global_variables_initializer()
    saver = tf.train.Saver()

    with tf.Session() as sess:
        sess.run(init_op)
        saver.restore(sess, "model2.ckpt")
        # print ("Model restored.")

        prediction = tf.argmax(y_conv, 1)

        return prediction.eval(feed_dict={x: [imvalue], keep_prob: 1.0}, session=sess)


with warnings.catch_warnings():
    warnings.simplefilter("ignore", category=PendingDeprecationWarning)

def imageprepare(argv):

    im = Image.open(argv).convert('L')
    width = float(im.size[0])
    height = float(im.size[1])
    newImage = Image.new('L', (28, 28), (255))  # creates white canvas of 28x28 pixels

    if width > height:  # check which dimension is bigger
        # Width is bigger. Width becomes 20 pixels.
        nheight = int(round((20.0 / width * height), 0))  # resize height according to ratio width
        if (nheight == 0):  # rare case but minimum is 1 pixel
            nheigth = 1
            # resize and sharpen
        img = im.resize((20, nheight), Image.ANTIALIAS).filter(ImageFilter.SHARPEN)
        wtop = int(round(((28 - nheight) / 2), 0))  # caculate horizontal pozition
        newImage.paste(img, (4, wtop))  # paste resized image on white canvas
    else:
        # Height is bigger. Heigth becomes 20 pixels.
        nwidth = int(round((20.0 / height * width), 0))  # resize width according to ratio height
        if (nwidth == 0):  # rare case but minimum is 1 pixel
            nwidth = 1
            # resize and sharpen
        img = im.resize((nwidth, 20), Image.ANTIALIAS).filter(ImageFilter.SHARPEN)
        wleft = int(round(((28 - nwidth) / 2), 0))  # caculate vertical pozition
        newImage.paste(img, (wleft, 4))  # paste resized image on white canvas

    # newImage.save("sample.png")

    tv = list(newImage.getdata())  # get pixel values

    # normalize pixels to 0 and 1. 0 is pure white, 1 is pure black.
    tva = [(255 - x) * 1.0 / 255.0 for x in tv]
    return tva
    # print(tva)

def main(argv):

    imvalue = imageprepare(argv)
    predint = predictint(imvalue)
    print (predint[0])  # first value in list

if __name__ == "__main__":
    main(sys.argv[1])      

2 个答案:

答案 0 :(得分:1)

我也使用这个脚本,我有同样的问题。我用这段代码解决它:

probabilities=y_conv
prob = probabilities.eval(feed_dict={x: [imvalue], keep_prob: 1.0}, session=sess)
probstr = str(prob)

这给你一个这样的百分比:0,000007或0,12456,ecc。 数字' 0,12456'意味着你有12%的认可。

答案 1 :(得分:0)

line prediction = tf.argmax(y_conv, 1)之后。添加以下代码

probs = tf.nn.softmax(y_conv)
probArray = sess.run(probs, feed_dict={x: [imvalue] })
prob_value = probArray[0][prediction.take(0)]
print(prob_value)

这样就可以计算张量流中的预测概率。