在我开始解释之前,这是实际情况。看看图片。。。在
我按顺序:
predict_2.py
是最重要的一个你可以找到我使用的项目here。在
所以,这就是我需要做的:一旦Tensorflow用predict_2.py
文件启动(通过CMD),它将返回(在CMD命令之后)我发送给它的图像中的数字。在
所以,我有图像(1),发送命令(2)TF做识别,数字被打印在CMD(3)中。在
现在,如您所见,文件夹中有更多的数字/整数/数字。 第一个问题:我怎么能把它们都扔出去? 第二:在CMD中的输出之后,我如何在一个文件(例如txt)中打印/保存它们(所有的数字,而不是一个)?在
predict_2.py
代码如下:
"""
Predict a handwritten integer (MNIST expert).
Script requires
1) saved model (model2.ckpt file) in the same location as the script is run from.
(requried a model created in the MNIST expert tutorial)
2) one argument (png file location of a handwritten integer)
Documentation at:
http://niektemme.com/ @@to do
"""
#import modules
import sys
import tensorflow as tf
from PIL import Image, ImageFilter
import os
from datetime import datetime
def predictint(imvalue):
"""
This function returns the predicted integer.
The input is the pixel values from the imageprepare() function.
"""
# 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.initialize_all_variables()
saver = tf.train.Saver()
"""
Load the model2.ckpt file
file is stored in the same directory as this python script is started
Use the model to predict the integer. Integer is returend as list.
Based on the documentatoin at
https://www.tensorflow.org/versions/master/how_tos/variables/index.html
"""
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)
def imageprepare(argv):
"""
This function returns the pixel values.
The input is a png file location.
"""
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):
"""
Main function.
"""
imvalue = imageprepare(argv)
predint = predictint(imvalue)
print (predint[0]) #first value in list
if __name__ == "__main__":
main(sys.argv[1])
需要修改什么? 我已经有代码,可以自动创建一个文件,但它是空的(甚至没有一个检测到的数字)。在
提前谢谢。对我来说,这不是一件容易的事,我会非常感谢你的帮助。在
目前没有回答
相关问题 更多 >
编程相关推荐