我正在训练一个神经网络，以使用notMNIST数据集识别字符，但是一旦运行，它的精度在每次迭代后都保持相对恒定。
我已经尝试过降低学习率，但是没有什么不同。可能是什么问题？
我认为问题可能出在tf.nn.relu（）方法的实现以及如何计算预测上，因为我在Tensor Flow和神经网络领域还很新
这是我的程序正在运行的屏幕截图，您可以看到训练集，验证集和测试集的准确性都非常差
num_steps=801
def accuracy(predictions, labels):
return (100.0 * np.sum(np.argmax(predictions,1) == np.argmax(labels,1))
/ predictions.shape[0])
with tf.Session(graph=graph) as session:
#this is a one-time operation which ensure the parameters get initialized
#we described in the graph: random weights for the matrix, zeros for the
#biases.
tf.global_variables_initializer().run()
print("initialized")
for step in range(num_steps):
#run the computations. we tell .run() that we want to run the optimizer,
#and get the loss value and the training predictions returned as numpy
#arrays.
_, l, predictions = session.run([optimizer,loss, train_prediction])
if (step % 100 ==0):
print("loss at step %d: %f" % (step,l))
print("Training accuracy: %.1f%%" % accuracy(
predictions, train_labels[:train_subset,:]))
#calling .eval() on valid_prediction is basically like calling run(), but
#just to get that one numpy array. Note that it recomputes all its graph
#dependencies.
print("Validation accuracy: %.1f%%" % accuracy(
valid_prediction.eval(), valid_labels))
print("test accuracy: %.1f%%" % accuracy(test_prediction.eval(),test_labels))
batch_size = 128
hidden_nodes = 1024
graph = tf.Graph()
with graph.as_default():
#input data. For the training data, we use a placeholder that will be fed
#at run time with a training minibatch
tf_train_dataset = tf.placeholder(tf.float32,
shape=(batch_size, image_size*image_size), name="td")
tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels), name="tl")
tf_valid_dataset = tf.constant(valid_dataset)
tf_test_dataset = tf.constant(test_dataset)
#variables
weights1 = tf.Variable(
tf.truncated_normal([image_size*image_size, hidden_nodes]))
biases1 = tf.Variable(tf.zeros([hidden_nodes]))
weights2 =tf.Variable(
tf.truncated_normal([hidden_nodes, num_labels]))
biases2 = tf.Variable(tf.zeros([num_labels]))
#training computation.
relu1 = tf.nn.relu(tf.matmul(tf_train_dataset, weights1) + biases1)
relu_out= tf.nn.relu(tf.matmul(relu1, weights2) + biases2)
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=relu_out,labels=tf_train_labels))
#optimizer
optimizer = tf.train.GradientDescentOptimizer(0.25).minimize(loss)
#predictions for the training, validation, and test data
train_prediction = relu_out
valid_prediction = tf.nn.relu(tf.matmul(tf.nn.relu(tf.matmul(tf_valid_dataset, weights1) + biases1), weights2) + biases2)
test_prediction = tf.nn.relu(tf.matmul(tf.nn.relu(tf.matmul(tf_test_dataset, weights1) + biases1), weights2) + biases2)
num_steps = 3001
with tf.Session(graph=graph) as session:
tf.global_variables_initializer().run()
print("initialized")
for step in range(num_steps):
#pick an offset within the training data, which has been randomized.
#note: we could use better randomization across epochs.
offset = (step * batch_size) % (train_labels.shape[0] - batch_size)
#generate a minibatch.
batch_data = train_dataset[offset:(offset + batch_size), :]
batch_labels = train_labels[offset:(offset + batch_size), :]
#prepare a dictionary telling the session where to feed the minibatch.
#the key of the dictionary is the placeholder node of the graph to be fed,
#and the value is the numpy array to feed to it
feed_dict = {tf_train_dataset : batch_data, tf_train_labels : batch_labels}
_, l, predictions = session.run(
[optimizer, loss, train_prediction], feed_dict=feed_dict)
if (step % 500 == 0):
print("minibatch loss at step %d: %f" % (step,l))
print("minibatch accuracy: %.1f%%" % accuracy(predictions,batch_labels))
print("validation accuracy: %.1f%%" % accuracy(
valid_prediction.eval(), valid_labels))
print("test accuracy: %.1f%%" % accuracy(test_prediction.eval(), test_labels))
最佳答案
如我所想，问题在于relu（）方法的实现。
在计算部分中，我使用了relu（）2次，而我本应该只使用一次。更改后，它最终看起来像这样。
logits_1 = tf.matmul(tf_train_dataset, weights1) + biases1
relu1 = tf.nn.relu(logits_1)
logits_2 = tf.matmul(relu1, weights2) + biases2
然后将损失变量中的参数logits从relu_out更改为logits_2。
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=logits_2,labels=tf_train_labels))
最后，我更改了预测变量，以便使用logits_2而不是relu_out进行计算。
train_prediction = tf.nn.softmax(logits_2)
valid_prediction = tf.nn.softmax(
tf.matmul(tf.nn.relu(tf.matmul(tf_valid_dataset,weights1) +biases1), weights2) + biases2)
test_prediction = tf.nn.softmax(
tf.matmul(tf.nn.relu(tf.matmul(tf_test_dataset, weights1) + biases1), weights2) + biases2)
如您所见，准确性提高了大约90％
尽管我仍然不确定为什么两次实施relu（）方法是一个问题。如果我没看错，relu（）方法返回0或给出的参数值，那么它不应该是一样的吗？
如果有人知道，请随时回答
关于python - 我的神经网络无法提高其准确性，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/47956261/