Question

我的问题如下：我实现了一个简单的FNN前馈网络，该网络接收90个输入并产生一个连续值作为输出。 FNN中的所有内容看起来都运行良好，但是我的任务是使用CNN进行类似类型的网络。从我能想到的是，我将输入90个特征作为9x10矩阵，从这里开始一切都变得不清楚。我不知道如何制作CONV和POL层，它们应该是几层？另外，对我来说，一个大问题是如何制作最后一层，以便可以给我连续的值作为输出而不是类别？

您能给我一些使用CNN做这些事情的地方吗？我正在使用以下模板并对其进行修改：

# Training Parameters
learning_rate = 0.01
num_steps = 200
batch_size = 5000
display_step = 10

# Network Parameters
num_input = 90  # MNIST data input (img shape: 28*28)
# num_classes = 10  # MNIST total classes (0-9 digits)
n_out = 1
dropout = 0.0  # Dropout, probability to keep units
total_len = X_train.shape[0]

# tf Graph input
X = tf.placeholder(tf.float32, [None, num_input])
Y = tf.placeholder(tf.float32, [None])
keep_prob = tf.placeholder(tf.float32)  # dropout (keep probability)


# Create some wrappers for simplicity
def conv2d(x, W, b, strides=1):
    # Conv2D wrapper, with bias and relu activation
    x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')
    x = tf.nn.bias_add(x, b)
    return tf.nn.relu(x)


def maxpool2d(x, k=2):
    # MaxPool2D wrapper
    return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1],
                          padding='SAME')


# Create model
def conv_net(x, weights, biases, dropout):
    # MNIST data input is a 1-D vector of 784 features (28*28 pixels)
    # Reshape to match picture format [Height x Width x Channel]
    # Tensor input become 4-D: [Batch Size, Height, Width, Channel]
    x = tf.reshape(x, shape=[-1, 9, 10, 1])

    # Convolution Layer
    conv1 = conv2d(x, weights['wc1'], biases['bc1'])
    # Max Pooling (down-sampling)
    conv1 = maxpool2d(conv1, k=2)

    # Convolution Layer
    conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
    # Max Pooling (down-sampling)
    conv2 = maxpool2d(conv2, k=2)

    # Fully connected layer
    # Reshape conv2 output to fit fully connected layer input
    fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])
    fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
    fc1 = tf.nn.relu(fc1)
    # Apply Dropout
    fc1 = tf.nn.dropout(fc1, dropout)

    # Output, class prediction
    out_layer = tf.matmul(fc1, weights['wout']) + biases['bout']
    return out_layer


# Store layers weight & bias
weights = {
    # 5x5 conv, 1 input, 32 outputs
    'wc1': tf.Variable(tf.random_normal([5, 5, 90, 92])),
    # 5x5 conv, 32 inputs, 64 outputs
    'wc2': tf.Variable(tf.random_normal([5, 5, 92, 94])),
    # fully connected, 7*7*64 inputs, 1024 outputs
    'wd1': tf.Variable(tf.random_normal([9 * 10 * 2, 90])),
    # 1024 inputs, 10 outputs (class prediction)
    'wout': tf.Variable(tf.random_normal([1024, n_out]))
}

biases = {
    'bc1': tf.Variable(tf.random_normal([32])),
    'bc2': tf.Variable(tf.random_normal([64])),
    'bd1': tf.Variable(tf.random_normal([1024])),
    'bout': tf.Variable(tf.random_normal([n_out]))
}

# Construct model
logits = conv_net(X, weights, biases, keep_prob)
prediction = tf.nn.softmax(logits)

# Define loss and optimizer
loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
    logits=logits, labels=Y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
train_op = optimizer.minimize(loss_op)

# Evaluate model
correct_pred = tf.equal(tf.argmax(prediction, 1), tf.argmax(Y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

# Initialize the variables (i.e. assign their default value)
init = tf.global_variables_initializer()

# Start training
with tf.Session() as sess:
    # Run the initializer
    sess.run(init)

    for step in range(1, num_steps + 1):

        total_batch = int(total_len / batch_size)  # 500/10
        # Loop over all batches
        for i in range(total_batch):
            batch_x = X_train[i * batch_size:(i + 1) * batch_size]
            batch_y = Y_train[i * batch_size:(i + 1) * batch_size]
            # Run optimization op (backprop)
            sess.run(train_op, feed_dict={X: batch_x, Y: batch_y, keep_prob: 0.8})
            if step % display_step == 0 or step == 1:
                # Calculate batch loss and accuracy
                loss, acc = sess.run([loss_op, accuracy], feed_dict={
                    X: batch_x,
                    Y: batch_y,
                    keep_prob: 1.0
                })
                print("Step " + str(step) + ", Minibatch Loss= " + \
                      "{:.4f}".format(loss) + ", Training Accuracy= " + \
                      "{:.3f}".format(acc))

    print("Optimization Finished!")

    # Calculate accuracy for 256 MNIST test images
    print("Testing Accuracy:", \
          sess.run(accuracy, feed_dict={
              X: X_test,
              Y: Y_test,
              keep_prob: 1.0
          }))

Answer 1

prediction = tf.nn.softmax(logits)

# Define loss and optimizer
loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
    logits=logits, labels=Y))

Softmax和交叉熵损失在这里并没有什么意义，考虑使用均方根损失：

cost = tf.reduce_mean(tf.square(output-ys))

有关详细信息，请参阅问题注释中链接的教程。

卷积神经网络用于预测连续输出

1 个答案: