如何使用CSV作为Tensorflow神经网络的输入数据?

时间:2016-11-13 01:57:16

标签: python csv tensorflow

我目前正试图通过略微改变MNIST for ML Beginners code来编写神经网络。我有一个像这样组织的CSV:

Image_Name |Nevus? |Dysplastic Nevus?| Melanoma? asdfgjkgdsl.png |1 |0 |0

图像名称,它是一个热门的结果。每张图像都是1022 x 767,我也希望将每个像素的颜色用作输入。因此,我将MNIST代码更改为2,351,622个输入(1022像素宽* 767像素高*每像素3种颜色)和3个输出。

# from tensorflow.examples.tutorials.mnist import input_data
# mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

def main():
    x = tf.placeholder(tf.float32, [None, 2351622])
    W = tf.Variable(tf.zeroes([2351622, 3]))
    b = tf.Variable(tf.zeroes([3]))

    y = tf.nn.softmax(tf.matmul(x, W) + b)

    y_ = tf.placeholder(tf.float32, [None, 3])
    cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
    train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

    init = tf.initialize_all_variables()
    sess = tf.Session()
    sess.run(init)

    for i in range(1000):
    example, label = sess.run([features, col5])
        # batch_xs, batch_ys = mnist.train.next_batch(100)
        # sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

    correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))

注释行是我必须替换以将我的数据加载到神经网络中的行。为每张图像(我已经找到)获取2.3M输入的最简单方法是:

from PIL import Image
import numpy as np

list(np.array(Image.open('asdfgjkgdsl.png')).ravel().flatten())

如何将此数据集加载到tensorflow中以用于训练神经网络?

1 个答案:

答案 0 :(得分:1)

推荐的方法可能是准备一系列tf_records个文件。 MNIST就是这样做的一个例子。然后,您创建一个队列。为了节省空间,最好将输入保持为png格式并在运行时使用decode_png

简而言之,首先转换(你应该写多个文件):

def _bytes_feature(value):
    return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))

def convert():
    writer = tf.python_io.TFRecordWriter(output_filename)
    for filename, nv, dnv, mn in parse_csv(...):
       fs = {}
       png_data = read_image_as_np_array(filename)
       image_name = 'data/image/png'
       fs['png_data'] = _bytes_feature(png_data)
       fs['label'] = _bytes_feature([nv, dnv, mn])
       example = tf.train.Example(features=tf.train.Features(feature=fs))
       writer.write(example.SerializeToString())
    writer.close()

然后,阅读它:(把它放在队列中)

reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_from_queue)
features_def = {
  'png_data': tf.FixedLenFeature([], tf.string),
  'label': tf.FixedLenFeature([3], tf.uint8)
}
features = tf.parse_single_example(serialized_example, features=feature_def)
image = tf.image.decode_png(features['png_data'])
...

您也可以使用tf.TextLineReader逐行阅读。