将numpy genfromtxt数据转换为TensorFlow Records文件格式

Question

我有两个numpy genfromtxt文件：第一个名为data_pixels的文件包含我的训练样例，每行为3072维，第二个名为classes_dataset，其中包含我的数据标签。

以下代码l使用此link的基础。 我的问题是Launch the graph part (see below)

batch_x, batch_y = mnist.train.next_batch(batch_size)

如何使我的两个向量（classes_dataset和data_pixels）适应这行代码以生成张量流批次？

这是我的代码：

import tensorflow as tf
import numpy as np
data_pixels=np.genfromtxt("pixels_dataset.csv", delimiter=',') #training data

data_pixels
array([[ 1.,  1.,  1., ...,  1.,  1.,  1.],
       [ 0.,  0.,  0., ...,  0.,  0.,  0.],
       [ 0.,  0.,  0., ...,  0.,  0.,  0.],
       ..., 
       [ 1.,  1.,  1., ...,  0.,  0.,  0.],
       [ 1.,  1.,  1., ...,  1.,  1.,  1.],
       [ 0.,  0.,  0., ...,  0.,  0.,  0.]])


data_pixels.shape
(2440, 3072)

班级

classes_dataset=np.genfromtxt("labels.csv",dtype=np.str , delimiter='\t')
classes_dataset
array(['m', 'm', 'i', ..., '3', '9', '9'], 
      dtype='|S5')

课程数量为：

a=len(c.Counter(set(classes_dataset)))
66

参数

 learning_rate = 0.001
    training_epochs = 15
    batch_size = 100
    display_step = 1
    n_hidden_1 = 256 # 1st layer number of features
    n_hidden_2 = 256 # 2nd layer number of features
    n_input= data_pixels.shape[1]
    n_classes = len(c.Counter(set(classes_dataset)))

tf图输入

x = tf.placeholder("float", [None, n_input])
y = tf.placeholder("float", [None, n_classes])

创建模型

def multilayer_perceptron(x, weights, biases):
    # Hidden layer with RELU activation
    layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1'])
    layer_1 = tf.nn.relu(layer_1)
    # Hidden layer with RELU activation
    layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
    layer_2 = tf.nn.relu(layer_2)
    # Output layer with linear activation
    out_layer = tf.matmul(layer_2, weights['out']) + biases['out']
    return out_layer

存储层重量＆amp;偏置

weights = {
    'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
    'h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
    'out': tf.Variable(tf.random_normal([n_hidden_2, n_classes]))
}
biases = {
    'b1': tf.Variable(tf.random_normal([n_hidden_1])),
    'b2': tf.Variable(tf.random_normal([n_hidden_2])),
    'out': tf.Variable(tf.random_normal([n_classes]))
}

构建模型

pred = multilayer_perceptron(x, weights, biases)

# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)

# Initializing the variables
init = tf.global_variables_initializer()

启动图表

with tf.Session() as sess:
    sess.run(init)

    # Training cycle
    for epoch in range(training_epochs):
        avg_cost = 0.
        #total_batch = int(mnist.train.num_examples/batch_size)
        total_batch = data_pixels.shape[0]/batch_size
        # Loop over all batches
        for i in range(total_batch):
            batch_x, batch_y = mnist.train.next_batch(batch_size) # How to put my dataset_pixels and classes_dataset into this format 
            # Run optimization op (backprop) and cost op (to get loss value)
            _, c = sess.run([optimizer, cost], feed_dict={x: batch_x,
                                                          y: batch_y})
            # Compute average loss
            avg_cost += c / total_batch
        # Display logs per epoch step
        if epoch % display_step == 0:
            print "Epoch:", '%04d' % (epoch+1), "cost=", \
                "{:.9f}".format(avg_cost)
    print "Optimization Finished!"

    # Test model
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
    # Calculate accuracy
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
    print "Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels})