1
我一直致力于在张量流中使用LeNet来训练和分类德国交通标志。我已经修改了LeNet的第一层和最后一层，以接受1和3通道彩色图像（第1层），并接受43 （第6层）的类数。用一次迭代更改训练数据后精度下降
from tensorflow.contrib.layers import flatten
def LeNet(x, inputdepth):
# Hyperparameters
mu = 0
sigma = 0.1
# Solution: Layer 1: Convolutional input 32x32x3. Output = 28x28x6
conv1_W = tf.Variable(tf.truncated_normal(shape=(5,5,inputdepth,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
# Solution: Activation
conv1 = tf.nn.relu(conv1)
# Solution: Pooling. INput = 28x28x6. Output = 14x14x6
conv1 = tf.nn.max_pool(conv1, ksize=[1,2,2,1], strides=[1,2,2,1], padding='VALID')
# Solution: 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
# Solution: Activation
conv2 = tf.nn.relu(conv2)
# Solution: Pooling. Input = 10x10x16. Output = 5x5x16
conv2 = tf.nn.max_pool(conv2, ksize=[1,2,2,1], strides = [1,2,2,1], padding='VALID')
# Solution: Flatten. Input = 5x5x16. Output = 400
fc0 = flatten(conv2)
# Solution: Layer 3: Full 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
# Solution: Activation
fc1 = tf.nn.relu(fc1)
# Solution: 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
# Solution: Activation
fc2 = tf.nn.relu(fc2)
# Solution: 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
由于网络被配置成同时接受1倍3的信道的图像，（与depth说法，我试图使用各种预处理方法（灰度级转换，0,1之间（归一化），并用缩放[ -0.5,0.5]）对输入训练图像，并试图评估每个步骤中的精度。我有6种处理的数据
- 原始RGB图像
- 的转换为灰度的灰度图像的
- 规范化[0,1]
- 具有零均值和单位方差缩放灰度图像之间[-0.5,0.5]
- 标准化在[0,1]
- 缩放上RGB之间的RGB图像具有零均值和单位方差[-0.5,0.5]
我想创造在一个循环中，它有一个类型预处理的数据的在一次迭代中，并且执行训练和验证一个管道。我的代码如下
inputData = [
('RGB',X_train, X_valid),
('RGBNormalized', normalizedRGB_train, normalizedRGB_valid),
('ScaledRGB', scaledRGB_train, scaledRGB_valid),
('Grayscale',grayimage_train, grayimage_valid),
('GrayScaleNormalized',normalizedGray_train, normalizedGray_valid),
('GrayScaleScaled',scaledGray_train, scaledGray_valid)
]
输入数据是元组的列表，其中在每个元组，ELEM [0]表示的名称，ELEM [1]表示的训练集和元素[2]表示的验证集。现在我的管道如下
def evaluate(X_data, y_data):
num_examples = len(X_data)
total_accuracy = 0
sess = tf.get_default_session()
for offset in range(0,num_examples, BATCH_SIZE):
batch_x, batch_y = X_data[offset:offset+BATCH_SIZE], y_data[offset:offset+BATCH_SIZE]
accuracy = sess.run(accuracy_operation, feed_dict = {x:batch_x, y:batch_y})
total_accuracy += (accuracy * len(batch_x))
return total_accuracy/num_examples
import tensorflow as tf
from sklearn.utils import shuffle
# Simulation Control Parameters
EPOCHS = 10
BATCH_SIZE = 128
rate = 0.0001
# Variable to store the accuracy of the model
model_performance = np.zeros((len(inputData),EPOCHS))
modelIndex = 0
for name,trainingData, validationData in inputData:
if np.shape(trainingData)[-1] == 3:
depth = 3
else:
depth = 1
# Create tensors for input data
x = tf.placeholder(tf.float32, (None, 32, 32,depth))
y = tf.placeholder(tf.int32, (None))
one_hot_y = tf.one_hot(y,43)
# Tensor Operations
logits = LeNet(x,depth)
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits,one_hot_y)
loss_operation = tf.reduce_mean(cross_entropy)
optimizer = tf.train.AdamOptimizer(learning_rate=rate)
training_operation = optimizer.minimize(loss_operation)
correct_prediction = tf.equal(tf.argmax(logits,1), tf.argmax(one_hot_y,1))
accuracy_operation = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# Pipeline for training and evaluation
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
num_examples = len(X_train)
print("Training on...",name,'data', 'with input size of',np.shape(trainingData))
print()
for i in range(EPOCHS):
X_train, y_train = shuffle(trainingData, y_train)
for offset in range(0, num_examples, BATCH_SIZE):
end = offset + BATCH_SIZE
batch_x, batch_y = X_train[offset:end], y_train[offset:end]
sess.run(training_operation, feed_dict = {x: batch_x, y: batch_y})
validation_accuracy = evaluate(validationData, y_valid)
print("EPOCH {} ...".format(i+1))
print("Validation Accuracy = {:.3f}".format(validation_accuracy))
print()
model_performance[modelIndex][i] = validation_accuracy
modelIndex = modelIndex + 1
sess.close()
如果我尽力培养与输入数据的网络，无需任何预处理，80％-90％之间的范围内的精度。但是保持网络环路下显示如下
Training on... RGB data with input size of (34799, 32, 32, 3)
EPOCH 1 ...
Training Accuracy = 0.038
Validation Accuracy = 0.598
EPOCH 2 ...
Training Accuracy = 0.057
Validation Accuracy = 0.055
EPOCH 3 ...
Training Accuracy = 0.057
Validation Accuracy = 0.055
EPOCH 4 ...
Training Accuracy = 0.058
Validation Accuracy = 0.054
EPOCH 5 ...
Training Accuracy = 0.057
Validation Accuracy = 0.054
Training on... RGBNormalized data with input size of (34799, 32, 32, 3)
EPOCH 1 ...
Training Accuracy = 0.054
Validation Accuracy = 0.042
EPOCH 2 ...
Training Accuracy = 0.047
Validation Accuracy = 0.049
EPOCH 3 ...
Training Accuracy = 0.054
Validation Accuracy = 0.048
EPOCH 4 ...
Training Accuracy = 0.057
Validation Accuracy = 0.054
EPOCH 5 ...
Training Accuracy = 0.054
Validation Accuracy = 0.048
Training on... ScaledRGB data with input size of (34799, 32, 32, 3)
EPOCH 1 ...
Training Accuracy = 0.056
Validation Accuracy = 0.054
EPOCH 2 ...
Training Accuracy = 0.057
Validation Accuracy = 0.054
EPOCH 3 ...
Training Accuracy = 0.057
Validation Accuracy = 0.054
EPOCH 4 ...
Training Accuracy = 0.057
Validation Accuracy = 0.055
EPOCH 5 ...
Training Accuracy = 0.057
Validation Accuracy = 0.055
Training on... Grayscale data with input size of (34799, 32, 32, 1)
EPOCH 1 ...
Training Accuracy = 0.056
Validation Accuracy = 0.051
EPOCH 2 ...
Training Accuracy = 0.058
Validation Accuracy = 0.049
EPOCH 3 ...
Training Accuracy = 0.056
Validation Accuracy = 0.049
EPOCH 4 ...
Training Accuracy = 0.055
Validation Accuracy = 0.050
EPOCH 5 ...
Training Accuracy = 0.056
Validation Accuracy = 0.050
Training on... GrayScaleNormalized data with input size of (34799, 32, 32, 1)
EPOCH 1 ...
Training Accuracy = 0.055
Validation Accuracy = 0.074
EPOCH 2 ...
Training Accuracy = 0.057
Validation Accuracy = 0.054
EPOCH 3 ...
Training Accuracy = 0.056
Validation Accuracy = 0.061
EPOCH 4 ...
Training Accuracy = 0.057
Validation Accuracy = 0.055
EPOCH 5 ...
Training Accuracy = 0.057
Validation Accuracy = 0.054
Training on... GrayScaleScaled data with input size of (34799, 32, 32, 1)
EPOCH 1 ...
Training Accuracy = 0.055
Validation Accuracy = 0.049
EPOCH 2 ...
Training Accuracy = 0.056
Validation Accuracy = 0.060
EPOCH 3 ...
Training Accuracy = 0.058
Validation Accuracy = 0.054
EPOCH 4 ...
Training Accuracy = 0.056
Validation Accuracy = 0.062
EPOCH 5 ...
Training Accuracy = 0.056
Validation Accuracy = 0.061
任何想法，我犯了一个错误滴管精度的奇怪的行为？
你可以发布与训练准确性相同的日志吗？ –
我修改了这个问题，包括每个数据的5个时期的训练和验证准确性 – Mechanic
看来你的网络根本没有训练。通过查看代码很难分辨出问题所在，但通常张量流图和训练操作看起来是正确的，所以我建议这个问题可能与数据有关。检查你加载和洗牌数据的方式。 –