python - Tensorflow conv3d_transpose *** 'python' : free(): invalid pointer 中的错误

Question

编辑打开的问题:https://github.com/tensorflow/tensorflow/issues/3128

我正在尝试使用新添加的 conv3d_transpose创建here

但我在标题中收到错误:*** Error in 'python': free(): invalid pointer

我的网络在 2D 模式下运行(使用相同的数据)，但它无法在 3D 模式下运行。

我在两台不同的 Linux 机器上尝试过，都运行 Ubuntu 14.04。我目前正在尝试让它在我的 Mac 上运行，但我找不到带有 conv3d_transpose 的版本包括。我必须在我的 Linux 机器上安装夜间构建，但 OSX 的夜间构建不包括它。有谁知道在哪里可以找到它吗？

我输入 3D 数据的方式可能是原因。我的数据输入为 2D 图像，我基本上将它们连接成 3D 矩阵。出于测试目的，我将数据集保持在较小的范围。我的批量大小是 1，深度是 5。我拉入 n_depth * batch_size来 self 的数据类，然后将其 reshape 为 [batch_size, n_depth, x, y, n_classes]

网络本身会构建，并且不会引发任何维度错误。该错误发生在第一次训练时。

完整代码如下:

import tensorflow as tf
import pdb
import numpy as np
from numpy import genfromtxt
from PIL import Image
from tensorflow.contrib.learn.python.learn.datasets.scroll import scroll_data

# Parameters
learning_rate = 0.001
training_iters = 1000000
batch_size = 1
display_step = 1

# Network Parameters
n_input_x = 200 # Input image x-dimension
n_input_y = 200 # Input image y-dimension
n_depth = 5
n_classes = 2 # Binary classification -- on a surface or not

dropout = 0.75 # Dropout, probability to keep units

# tf Graph input
x = tf.placeholder(tf.float32, [None, n_depth, n_input_x, n_input_y])
y = tf.placeholder(tf.float32, [None, n_depth, n_input_x, n_input_y, n_classes], name="ground_truth")
keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)


# This function converts the ground truth data into a
    # 2 channel classification -- n_input_x x n_input_y x 2
    # one layer for 0's and the other for 1's
def convert_to_2_channel(x, size):
    #assume input has dimension (batch_size,x,y)
    #output will have dimension (batch_size,x,y,2)
    output = np.empty((size, 200, 200, 2))

    temp_temp_arr1 = np.empty((size, 200, 200))
    temp_temp_arr2 = np.empty((size, 200, 200))

    for i in xrange(size):
        for j in xrange(n_input_x):
            for k in xrange(n_input_y):
                if x[i][j][k] == 1:
                    temp_temp_arr1[i][j][k] = 1
                    temp_temp_arr2[i][j][k] = 0
                else:
                    temp_temp_arr1[i][j][k] = 0
                    temp_temp_arr2[i][j][k] = 1

    for i in xrange(size):
        for j in xrange(n_input_x):
            for k in xrange(n_input_y):
                for l in xrange(2):
                    try:
                        if l == 0:
                            output[i][j][k][l] = temp_temp_arr1[i][j][k]
                        else:
                            output[i][j][k][l] = temp_temp_arr2[i][j][k]
                    except IndexError:
                        print "Index error"
                        pdb.set_trace()
    return output


# Create some wrappers for simplicity
def conv3d(x, W, b, strides=1):
    # Conv2D wrapper, with bias and relu activation
    x = tf.nn.conv3d(x, W, strides=[1, strides, strides, strides, 1], padding='SAME')
    x = tf.nn.bias_add(x, b)
    return tf.nn.relu(x)

def maxpool3d(x, k=2):
    # MaxPool2D wrapper
    return tf.nn.max_pool3d(x, ksize=[1, k, k, k, 1], strides=[1, k, k, k, 1],
                          padding='SAME')

def deconv3d(prev_layer, w, b, output_shape, strides):
    # Deconv layer
    deconv = tf.nn.conv3d_transpose(prev_layer, w, output_shape=output_shape, strides=strides, padding="VALID")
    deconv = tf.nn.bias_add(deconv, b)
    deconv = tf.nn.relu(deconv)
    return deconv

# Create model
def conv_net(x, weights, biases, dropout):
    # Reshape input picture
    x = tf.reshape(x, shape=[-1, 5, 200, 200, 1])

    with tf.name_scope("conv1") as scope:
    # Convolution Layer
        conv1 = conv3d(x, weights['wc1'], biases['bc1'])
        # Max Pooling (down-sampling)
        #conv1 = tf.nn.local_response_normalization(conv1)
        conv1 = maxpool3d(conv1, k=2)

    # Convolution Layer
    with tf.name_scope("conv2") as scope:
        conv2 = conv3d(conv1, weights['wc2'], biases['bc2'])
        # Max Pooling (down-sampling)
        # conv2 = tf.nn.local_response_normalization(conv2)
        conv2 = maxpool3d(conv2, k=2)

    # Convolution Layer
    with tf.name_scope("conv3") as scope:
        conv3 = conv3d(conv2, weights['wc3'], biases['bc3'])
        # Max Pooling (down-sampling)
        # conv3 = tf.nn.local_response_normalization(conv3)
        conv3 = maxpool3d(conv3, k=2)

    pdb.set_trace()

    temp_batch_size = tf.shape(x)[0] #batch_size shape
    with tf.name_scope("deconv1") as scope:
        output_shape = [temp_batch_size, 2, 50, 50, 64]
        strides = [1,1,2,2,1]
        conv4 = deconv3d(conv3, weights['wdc1'], biases['bdc1'], output_shape, strides)
        # conv4 = tf.nn.local_response_normalization(conv4)

    with tf.name_scope("deconv2") as scope:
        output_shape = [temp_batch_size, 3, 100, 100, 32]
        strides = [1,1,2,2,1]
        conv5 = deconv3d(conv4, weights['wdc2'], biases['bdc2'], output_shape, strides)
        # conv5 = tf.nn.local_response_normalization(conv5)

    with tf.name_scope("deconv3") as scope:
        output_shape = [temp_batch_size, 5, 200, 200, 2]
        #this time don't use ReLu -- since output layer
        conv6 = tf.nn.conv3d_transpose(conv5, weights['wdc3'], output_shape=output_shape, strides=[1,1,2,2,1], padding="VALID")
        conv6 = tf.nn.bias_add(conv6, biases['bdc3'])
        # conv6 = tf.nn.relu(conv6)

    # Include dropout
    #conv6 = tf.nn.dropout(conv6, dropout)
    return conv6

weights = {
    # 5x5 conv, 1 input, 32 outputs
    'wc1' : tf.Variable(tf.random_normal([5, 5, 5, 1, 32])),
    # 5x5 conv, 32 inputs, 64 outputs
    'wc2' : tf.Variable(tf.random_normal([3, 5, 5, 32, 64])),
    # 5x5 conv, 32 inputs, 64 outputs
    'wc3' : tf.Variable(tf.random_normal([2, 5, 5, 64, 128])),

    'wdc1' : tf.Variable(tf.random_normal([2, 2, 2, 64, 128])),

    'wdc2' : tf.Variable(tf.random_normal([2, 2, 2, 32, 64])),

    'wdc3' : tf.Variable(tf.random_normal([3, 2, 2, 2, 32])),
}

biases = {
    'bc1': tf.Variable(tf.random_normal([32])),
    'bc2': tf.Variable(tf.random_normal([64])),
    'bc3': tf.Variable(tf.random_normal([128])),
    'bdc1': tf.Variable(tf.random_normal([64])),
    'bdc2': tf.Variable(tf.random_normal([32])),
    'bdc3': tf.Variable(tf.random_normal([2])),
}

# Construct model
# with tf.name_scope("net") as scope:
pred = conv_net(x, weights, biases, keep_prob)
pdb.set_trace()
pred = tf.reshape(pred, [-1, n_input_x, n_input_y, n_depth, n_classes]) #Reshape to shape-Y

# Define loss and optimizer
# Reshape for cost function
temp_pred = tf.reshape(pred, [-1, 2])
temp_y = tf.reshape(y, [-1, 2])
with tf.name_scope("loss") as scope:
    # cost = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(pred, y))
    cost = (tf.nn.softmax_cross_entropy_with_logits(temp_pred, temp_y))

with tf.name_scope("opt") as scope:
    optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)

# Evaluate model
with tf.name_scope("acc") as scope:
    # accuracy is the difference between prediction and ground truth matrices
    correct_pred = tf.equal(0,tf.cast(tf.sub(tf.nn.softmax(temp_pred),temp_y), tf.int32))
    accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

# Initializing the variables
init = tf.initialize_all_variables()
saver = tf.train.Saver()
# Launch the graph
with tf.Session() as sess:
    sess.run(init)
    summary = tf.train.SummaryWriter('/tmp/logdir/', sess.graph) #initialize graph for tensorboard
    step = 1
    # Import data
    data = scroll_data.read_data('/home/kendall/Desktop/')
    # Keep training until reach max iterations
    while step * batch_size < training_iters:
        batch_x, batch_y = data.train.next_batch(n_depth)
        # Run optimization op (backprop)
        batch_x = batch_x.reshape((batch_size, n_depth, n_input_x, n_input_y))
        batch_y = batch_y.reshape((n_depth, n_input_x, n_input_y))
        batch_y = convert_to_2_channel(batch_y, n_depth) # Converts the 200x200 ground truth to a 200x200x2 classification
        batch_y = batch_y.reshape(batch_size * n_input_x * n_input_y * n_depth, 2)
        sess.run(optimizer, feed_dict={x: batch_x, temp_y: batch_y,
                                       keep_prob: dropout})

        pdb.set_trace()
        if step % display_step == 0:
            batch_y = batch_y.reshape(batch_size, n_input_x, n_input_y, 2)
            loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,
                                                              y: batch_y,
                                                              keep_prob: 1.0})
            print "Accuracy = " + str(acc)
            #print "Loss = " + str(loss)

            # Save network and make prediction
            if acc > 0.7:
                # Save network
                save_path = "model.ckpt"
                saver.save(sess, save_path)

                # Make prediction
                im = Image.open('/home/kendall/Desktop/HA900_frames/frame0001.tif')
                batch_x = np.array(im)
                batch_x = batch_x.reshape((1, n_input_x, n_input_y))
                batch_x = batch_x.astype(float)
                prediction = sess.run(pred, feed_dict={x: batch_x, keep_prob: 1.0})
                prediction = prediction.reshape((40000,2))
                prediction = tf.nn.softmax(prediction)
                prediction = prediction.eval()
                prediction = prediction.reshape((n_input_x, n_input_y, 2))

                # Temp arrays are to splice the prediction n_input_x x n_input_y x 2
                    # into 2 matrices n_input_x x n_input_y
                temp_arr1 = np.empty((n_input_x, n_input_y))
                temp_arr2 = np.empty((n_input_x, n_input_y))
                for i in xrange(n_input_x):
                    for j in xrange(n_input_x):
                        for k in xrange(2):
                            if k == 0:
                                temp_arr1[i][j] = prediction[i][j][k]
                            else:
                                temp_arr2[i][j] = prediction[i][j][k]
                # np.savetxt("small_dataset_1.csv", temp_arr1, delimiter=",")
                # np.savetxt("small_dataset_2.csv", temp_arr2, delimiter=",")

                if acc > 0.70 and acc < 0.73:
                    np.savetxt("run_1_step_1-1.csv", temp_arr1, delimiter=",")
                    # np.savetxt("run_1_step_1-2.csv", temp_arr2, delimiter=",")
                if acc > 0.73 and acc < 0.78:
                    np.savetxt("run_1_step_2-1.csv", temp_arr1, delimiter=",")
                    # np.savetxt("run_1_step_2-2.csv", temp_arr2, delimiter=",")
                if acc > 0.78 and acc < 0.81:
                    np.savetxt("run_1_step_3-1.csv", temp_arr1, delimiter=",")
                    # np.savetxt("run_1_step_3-2.csv", temp_arr2, delimiter=",")
                if acc > 0.81 and acc < 0.84:
                    np.savetxt("run_1_step_4-1.csv", temp_arr1, delimiter=",")
                    # np.savetxt("run_1_step_4-2.csv", temp_arr2, delimiter=",")
                if acc > 0.84 and acc < 0.87:
                    np.savetxt("run_1_step_5-1.csv", temp_arr1, delimiter=",")
                    # np.savetxt("run_1_step_5-2.csv", temp_arr2, delimiter=",")
                if acc > 0.87 and acc < 0.9:
                    np.savetxt("run_1_step_6-1.csv", temp_arr1, delimiter=",")
                    # np.savetxt("run_1_step_6-2.csv", temp_arr2, delimiter=",")
                if acc > 0.9 and acc < 0.95:
                    np.savetxt("run_1_step_7-1.csv", temp_arr1, delimiter=",")
                    # np.savetxt("run_1_step_7-2.csv", temp_arr2, delimiter=",")
                if acc > 0.95:
                    np.savetxt("run_1_step_8-1.csv", temp_arr1, delimiter=",")
                    # np.savetxt("run_1_step_8-2.csv", temp_arr2, delimiter=",")


            if acc > 0.98:
                break

        step += 1
    print "Optimization Finished!"

    # Measure accuracy on test set
    print "Testing Accuracy:",
    test_img = data.test.labels[0:].reshape((5, n_input_x, n_input_y))
    test_img = convert_to_2_channel(test_img, 5)
    acc = sess.run(accuracy, feed_dict={x: data.test.images[0:].reshape((5, n_input_x, n_input_y)),
                                      y: test_img,
                                      keep_prob: 1.})
    print acc

Answer 1

您可能需要安装libtcmalloc-minimal4。

 sudo apt-get install libtcmalloc-minimal4

并导出其路径:

 export LD_PRELOAD="/usr/lib/libtcmalloc_minimal.so.4"