CNN实施

Question

我正在尝试建立网络以对许多样本的雷达图像进行图像分类，分为塑料和金属物体两类。在Matlab中处理后的图像大小为28 * 28像素，图像总数为463张图像，包含上述2类。经过训练的输出标签根据图像的类别给出01和10的输出。

# Parameter definitions
training_iters = 100 
learning_rate = 0.001
batch_size = 30

# GPR data input (img shape: 28*28)
n_input = 28

# GPR classes (0-1 digits)
n_classes = 2

#create placeholders for the inputs and labels 
x = tf.placeholder("float", [None, 28,28,1])
y = tf.placeholder("float", [None, n_classes])

##Creating 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):
    return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1],padding='SAME')

## Define the network architecture
def conv_net(x, weights, biases):  

    # here we call the conv2d function we had defined above and pass the input image x, weights wc1 and bias bc1.
    conv1 = conv2d(x, weights['wc1'], biases['bc1'])
    # Max Pooling (down-sampling), this chooses the max value from a 2*2 matrix window and outputs a 14*14 matrix.
    conv1 = maxpool2d(conv1, k=2)


    # Dropou layer to avoid overfitting (added layers)
    Conv1 = tf.layers.dropout(inputs=conv1, rate=0.4, training=biases == tf.estimator.ModeKeys.TRAIN)
    # Convolution Layer
    # here we call the conv2d function we had defined above and pass the input image x, weights wc2 and bias bc2.
    conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
    # Max Pooling (down-sampling), this chooses the max value from a 2*2 matrix window and outputs a 7*7 matrix.
    conv2 = maxpool2d(conv2, k=2)
    Conv2 = tf.layers.dropout(inputs=conv2, rate=0.4, training=biases == tf.estimator.ModeKeys.TRAIN)

    conv3 = conv2d(conv2, weights['wc3'], biases['bc3'])
    # Max Pooling (down-sampling), this chooses the max value from a 2*2 matrix window and outputs a 4*4.
    conv3 = maxpool2d(conv3, k=2)
   # Conv3 = tf.layers.dropout(inputs=conv3, rate=0.4, training=biases == tf.estimator.ModeKeys.TRAIN)


    # Fully connected layer
    # Reshape conv2 output to fit fully connected layer input
    fc1 = tf.reshape(conv3, [-1, weights['wd1'].get_shape().as_list()[0]])
    fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
    fc1 = tf.nn.relu(fc1)
    # Output, class prediction
    # finally we multiply the fully connected layer with the weights and add a bias term. 
    out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])
    return out

## Loss and Optimizer Nodes (Here is the problem)

pred = conv_net(x, weights, biases)

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)

##Evauate model
#Check whether the index of the maximum value of the predicted image is equal to the actual labelled image.
correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))

#calculate accuracy across all the given images and average them out. 
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

# Initializing the variables
init = tf.global_variables_initializer()

## Training and Testing the Model
with tf.Session() as sess:
    sess.run(init) 
    train_loss = []
    test_loss = []
    train_accuracy = []
    test_accuracy = []
    summary_writer = tf.summary.FileWriter('./Output', sess.graph)
    for i in range(training_iters):
        for batch in range(len(train_X)//batch_size):
            batch_x = train_X[batch*batch_size:min((batch+1)*batch_size,len(train_X))]
            batch_y = train_y[batch*batch_size:min((batch+1)*batch_size,len(train_y))]    
            # Run optimization op (backprop).
                # Calculate batch loss and accuracy
            opt = sess.run(optimizer, feed_dict={x: batch_x,
                                                              y: batch_y})
            loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,
                                                              y: batch_y})
        print("Iter " + str(i) + ", Loss= " + \
                      "{:.6f}".format(loss) + ", Training Accuracy= " + \
                      "{:.5f}".format(acc))
        print("Optimization Finished!")

        # Calculate accuracy for all 10000 mnist test images
        test_acc,valid_loss = sess.run([accuracy,cost], feed_dict={x: test_X,y : test_y})
        train_loss.append(loss)
        test_loss.append(valid_loss)
        train_accuracy.append(acc)
        test_accuracy.append(test_acc)
        print("Testing Accuracy:","{:.5f}".format(test_acc))
    summary_writer.close()

运行训练后，网络会为训练准确性（值为1）和测试准确性（值为0.52）给出固定值。有什么建议吗？