dimanche 24 décembre 2017

I can not sample well using "tf.boolean _ mask."

My Enviroment Windows10 Anaconda Tensorflow 1.1.0 Python 3.5

I classify images using a neural network. I use an image of 1024 * 768 pixels, but since the calculation amount is enormous when using all the pixels, I introduced a random mask to randomly sample 1000 pixels. However, this kind of error has occurred and it has not been successfully sampled successfully

”ValueError: Dimensions must be equal, but are 786432 and 1728 for 'fc1/MatMul' (op: 'MatMul') with input shapes: [?,786432], [1000,10].”

Why does it look like this? Could you tell me if there is a solution?

All codes are posted below.

import sys
sys.path.append('/usr/local/opt/opencv3/lib/python3.5.4/site-packages')
import cv2
import numpy as np
import tensorflow as tf
import tensorflow.python.platform
import tensorboard as tb   
import os
import math
import time
import random
start_time = time.time()



# TensorBoard output information directory
log_dir = '/tmp/data1'  #tensorboard --logdir=/tmp/data1

#directory delete and reconstruction
if tf.gfile.Exists(log_dir):
    tf.gfile.DeleteRecursively(log_dir)
tf.gfile.MakeDirs(log_dir)



# Reserve memory
config = tf.ConfigProto(
   gpu_options=tf.GPUOptions(
       allow_growth=True
   )
)
sess = sess = tf.Session(config=config)




NUM_CLASSES = 2
IMAGE_SIZE_x = 1024
IMAGE_SIZE_y = 768
IMAGE_CHANNELS = 1
IMAGE_PIXELS = IMAGE_SIZE_x*IMAGE_SIZE_y*IMAGE_CHANNELS
SAMPLE_PIXELS = 1000

flags = tf.app.flags
FLAGS = flags.FLAGS
flags.DEFINE_string('train', 'train.txt', 'File name of train data')
flags.DEFINE_string('test', 'test.txt', 'File name of train data')
flags.DEFINE_string('image_dir', 'data', 'Directory of images')
flags.DEFINE_string('train_dir', '/tmp/data', 'Directory to put the training data.')
flags.DEFINE_integer('max_steps', 20000, 'Number of steps to run trainer.')
flags.DEFINE_integer('batch_size', 10, 'Batch size'
                     'Must divide evenly into the dataset sizes.')
flags.DEFINE_float('learning_rate', 1e-5, 'Initial learning rate.')


# 

def inference(images_placeholder, keep_prob):
    """ Function to create predictive model

   argument:
        images_placeholder: image placeholder
        keep_prob: dropout rate placeholder

    Return:
        y_out: 
    """
    # Initialie with normal distribution with weight of 0.1
    def weight_variable(shape):
      initial = tf.truncated_normal(shape, stddev=0.1)
      return tf.Variable(initial)

    # Initialized with normal distribution with bias of 0.1
    def bias_variable(shape):
      initial = tf.constant(0.1, shape=shape)
      return tf.Variable(initial)

# Random mask
mask = np.array([False]*IMAGE_PIXELS)
inds = np.random.choice(np.arange(IMAGE_PIXELS),size = SAMPLE_PIXELS)
mask[inds] = True

# Sample input
x_image = tf.boolean_mask(images_placeholder,mask)

    # input
    with tf.name_scope('fc1') as scope:
        W_fc1 = weight_variable([SAMPLE_PIXELS,10])
        b_fc1 = bias_variable([10])
        h_fc1 = tf.nn.relu(tf.matmul(x_image,W_fc1) + b_fc1)

    # hidden
    with tf.name_scope('fc2') as scope:
        W_fc2 = weight_variable([10,10])
        b_fc2 = bias_variable([10])
        h_fc2 = tf.nn.relu(tf.matmul(h_fc1,W_fc2) + b_fc2)


    # output
    with tf.name_scope('fc3') as scope:
        W_fc5 = weight_variable([10,2])
        b_fc5 = bias_variable([2])

    # softmax regression
    with tf.name_scope('softmax') as scope:
        y_out=tf.nn.softmax(tf.matmul(h_fc4, W_fc5) + b_fc5)

    # return
    return y_out

def loss(logits, labels):
    """ loss function

    argument:
        logits: logit tensor, float - [batch_size, NUM_CLASSES]
        labels: labrl tensor, int32 - [batch_size, NUM_CLASSES]

    return value:
        cross_entropy:tensor, float

    """
    # cross entropy
    cross_entropy = -tf.reduce_sum(labels*tf.log(tf.clip_by_value(logits,1e-10,1.0)))
    # TensorBoard
    tf.summary.scalar("cross_entropy", cross_entropy)
    return cross_entropy

def training(loss, learning_rate):

    #Adam
    train_step = tf.train.AdamOptimizer(learning_rate).minimize(loss)
    return train_step

def accuracy(logits, labels):

    correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(labels, 1)) #original
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))#original
    tf.summary.scalar("accuracy", accuracy)#original
    return accuracy#original


if __name__ == '__main__':
    f = open(FLAGS.train, 'r')
    # array data
    train_image = []
    train_label = []
    for line in f:
        # Separate space and remove newlines
        line = line.rstrip()
        l = line.split()
        # Load data and resize
        img = cv2.imread(FLAGS.image_dir + '/' + l[0])
        img = cv2.resize(img, (IMAGE_SIZE_x, IMAGE_SIZE_y))
        #transrate grayscale
        img_gry = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
        # transrate one row and 0-1 float
        train_image.append(img_gry.flatten().astype(np.float32)/255.0)
        # Prepare with label 1-of-k method
        tmp = np.zeros(NUM_CLASSES)
        tmp[int(l[1])] = 1
        train_label.append(tmp)
    # transrate numpy
    train_image = np.asarray(train_image)
    train_label = np.asarray(train_label)
    f.close()

    f = open(FLAGS.test, 'r')
    test_image = []
    test_label = []
    for line in f:
        line = line.rstrip()
        l = line.split()
        img = cv2.imread(FLAGS.image_dir + '/' + l[0])
        img = cv2.resize(img, (IMAGE_SIZE_x, IMAGE_SIZE_y))
        #transrate grayscale
        img_gry = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
        #  transrate one row and 0-1 float
        test_image.append(img_gry.flatten().astype(np.float32)/255.0)
        tmp = np.zeros(NUM_CLASSES)
        tmp[int(l[1])] = 1
        test_label.append(tmp)
    test_image = np.asarray(test_image)
    test_label = np.asarray(test_label)
    f.close()

    with tf.Graph().as_default():
        # Put the image Tensor
        images_placeholder = tf.placeholder("float", shape=(None, IMAGE_PIXELS))
        # Put the label Tensor
        labels_placeholder = tf.placeholder("float", shape=(None, NUM_CLASSES))
        # Put dropout rate Tensor
        keep_prob = tf.placeholder("float")
        # Load inference() and make model
        logits = inference(images_placeholder, keep_prob)
        # Load loss() and calculate loss
        loss_value = loss(logits, labels_placeholder)
        # Load training() and train
        train_op = training(loss_value, FLAGS.learning_rate)
        # calculate accuracy
        acc = accuracy(logits, labels_placeholder)
        # save
        saver = tf.train.Saver()
        # Make Session
        sess = tf.Session()
        # Initialize variable
        sess.run(tf.global_variables_initializer())
        # TensorBoard
        summary_op = tf.summary.merge_all()
        summary_writer = tf.summary.FileWriter(FLAGS.train_dir, sess.graph)




# Start training
for step in range(FLAGS.max_steps):
    for i in range(int(len(train_image)/FLAGS.batch_size)):
        batch = FLAGS.batch_size*i
        sess.run(train_op, feed_dict={
          images_placeholder: train_image[batch:batch+FLAGS.batch_size],
          labels_placeholder: train_label[batch:batch+FLAGS.batch_size],
          keep_prob: 0.5})

    # Accuracy calculation for every steps
    train_accuracy = sess.run(acc, feed_dict={
        images_placeholder: train_image,
        labels_placeholder: train_label,
        keep_prob: 1.0})
    print("step %d, training accuracy %g" %(step, train_accuracy))


    # Added value to be displayed in Tensorflow every 1step
    summary_str = sess.run(summary_op, feed_dict={
        images_placeholder: train_image,
        labels_placeholder: train_label,
        keep_prob: 1.0})
    summary_writer.add_summary(summary_str, step)

    # Display accuracy on test data after training
    print("        test accuracy     %g"%sess.run(acc, feed_dict={
        images_placeholder: test_image,
        labels_placeholder: test_label,
        keep_prob: 1.0}))

    duration = time.time() - start_time

    print('%.3f sec' %duration)

    # Save model
    save_path = saver.save(sess, os.getcwd() + "\\model.ckpt")




Aucun commentaire:

Enregistrer un commentaire