Question

我正在使用LeNet识别交通信号图像。由于某些原因，我的管道无法正常工作，并且每个时期的培训和验证准确性完全没有变化。我在这里附上Jupyter Notebook（HTML文件），请帮助我确定代码中的问题。

def LeNet(x):
    mu = 0
    sigma = 0.1**

    # Layer 1: Convolutional. Input = 32x32x1. Output = 28x28x6.
    conv1_W = tf.Variable(tf.truncated_normal(shape=(5, 5, 1, 6), mean = mu, stddev = sigma))
    conv1_b = tf.Variable(tf.zeros(6))
    conv1   = tf.nn.conv2d(x, conv1_W, strides=[1, 1, 1, 1], padding='VALID') + conv1_b

    # Layer 1: Activation.
    conv1 = tf.nn.relu(conv1)

    # Layer 1: Pooling. Input = 28x28x6. Output = 14x14x6.
    conv1 = tf.nn.max_pool(conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID')

    # Layer 2: Convolutional. Output = 10x10x16.
    conv2_W = tf.Variable(tf.truncated_normal(shape=(5, 5, 6, 16), mean = mu, stddev = sigma))
    conv2_b = tf.Variable(tf.zeros(16))
    conv2   = tf.nn.conv2d(conv1, conv2_W, strides=[1, 1, 1, 1], padding='VALID') + conv2_b

    # Layer 2: Activation.
    conv2 = tf.nn.relu(conv2)

    # Layer 2: Pooling. Input = 10x10x16. Output = 5x5x16.
    conv2 = tf.nn.max_pool(conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID')

    # Layer 2: Flatten. Input = 5x5x16. Output = 400.
    fc0   = flatten(conv2)
    fc0   = tf.nn.dropout(fc0, keep_prob)

    # Layer 3: Fully Connected. Input = 400. Output = 120.
    fc1_W = tf.Variable(tf.truncated_normal(shape=(400, 120), mean = mu, stddev = sigma))
    fc1_b = tf.Variable(tf.zeros(120))
    fc1   = tf.matmul(fc0, fc1_W) + fc1_b

    # Layer 3: Activation.
    fc1    = tf.nn.relu(fc1)
    fc1    = tf.nn.dropout(fc1, keep_prob) 


    # Layer 4: Fully Connected. Input = 120. Output = 84.
    fc2_W  = tf.Variable(tf.truncated_normal(shape=(120, 84), mean = mu, stddev = sigma))
    fc2_b  = tf.Variable(tf.zeros(84))
    fc2    = tf.matmul(fc1, fc2_W) + fc2_b

    # Layer 4: Activation.
    fc2    = tf.nn.relu(fc2)
    fc2    = tf.nn.dropout(fc2, keep_prob) 


    # Layer 5: Fully Connected. Input = 84. Output = 43.
    fc3_W  = tf.Variable(tf.truncated_normal(shape=(84, 43), mean = mu, stddev = sigma))
    fc3_b  = tf.Variable(tf.zeros(43))


    logits = tf.matmul(fc2, fc3_W) + fc3_b

    return logits

这是上述模型的培训代码

with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
num_examples = len(X_train)
print("Training ...")
print()
validation_accuracies = []

for i in range(EPOCHS):
    X_train, X_train_processed, y_train = shuffle(X_train,X_train_processed,y_train)
    for offset in range(0, num_examples, BATCH_SIZE):
        end = offset + BATCH_SIZE
        batch_x, batch_y = X_train_processed[offset:end], y_train[offset:end]
        sess.run(training_operation, feed_dict={x: batch_x, y: batch_y, keep_prob: 1.0})

    training_accuracy = evaluate(X_train_processed, y_train)   
    validation_accuracy = evaluate(X_valid_processed, y_valid)

    print("EPOCH {} ...".format(i+1))
    print("Training Accuracy = {:.3f}".format(training_accuracy))
    print("Validation Accuracy = {:.3f}".format(validation_accuracy))
    print()
    validation_accuracies.append(validation_accuracy)

saver.save(sess, os.path.join(DIR, model_name))
plt.plot(range(EPOCHS),validation_accuracies)
plt.show

print("Model saved")

使用tensorflow的交通标志分类器为每个时期提供相同的验证和训练精度

0 个答案: