Python 3.x Udacity深度学习,作业3,第3部分:Tensorflow辍学函数
我现在正在参加Udacity深度学习班的作业3。我已经完成了它的大部分工作,但我注意到问题3,这是关于使用tensorflow的“辍学”,似乎降低了我的性能,而不是改善它 所以我觉得我做错了什么。我会把我的全部代码放在这里。如果有人能向我解释如何正确使用辍学,我将不胜感激。(或者确认我正确使用了它,但在这种情况下它没有帮助。)。它的准确率从94%以上(无脱落)下降到91.5%。如果不使用L2正则化,退化甚至更大Python 3.x Udacity深度学习,作业3,第3部分:Tensorflow辍学函数,python-3.x,tensorflow,deep-learning,anaconda,Python 3.x,Tensorflow,Deep Learning,Anaconda,我现在正在参加Udacity深度学习班的作业3。我已经完成了它的大部分工作,但我注意到问题3,这是关于使用tensorflow的“辍学”,似乎降低了我的性能,而不是改善它 所以我觉得我做错了什么。我会把我的全部代码放在这里。如果有人能向我解释如何正确使用辍学,我将不胜感激。(或者确认我正确使用了它,但在这种情况下它没有帮助。)。它的准确率从94%以上(无脱落)下降到91.5%。如果不使用L2正则化,退化甚至更大 def create_nn(dataset, weights_hidden, bia
def create_nn(dataset, weights_hidden, biases_hidden, weights_out, biases_out):
# Original layer
logits = tf.add(tf.matmul(tf_train_dataset, weights_hidden), biases_hidden)
# Drop Out layer 1
logits = tf.nn.dropout(logits, 0.5)
# Hidden Relu layer
logits = tf.nn.relu(logits)
# Drop Out layer 2
logits = tf.nn.dropout(logits, 0.5)
# Output: Connect hidden layer to a node for each class
logits = tf.add(tf.matmul(logits, weights_out), biases_out)
return logits
# Create model
batch_size = 128
hidden_layer_size = 1024
beta = 1e-3
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))
tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels))
tf_valid_dataset = tf.constant(valid_dataset)
tf_test_dataset = tf.constant(test_dataset)
# Variables.
weights_hidden = tf.Variable(
#tf.truncated_normal([image_size * image_size, num_labels]))
tf.truncated_normal([image_size * image_size, hidden_layer_size]))
#biases = tf.Variable(tf.zeros([num_labels]))
biases_hidden = tf.Variable(tf.zeros([hidden_layer_size]))
weights_out = tf.Variable(tf.truncated_normal([hidden_layer_size, num_labels]))
biases_out = tf.Variable(tf.zeros([num_labels]))
# Training computation.
#logits = tf.matmul(tf_train_dataset, weights_out) + biases_out
logits = create_nn(tf_train_dataset, weights_hidden, biases_hidden, weights_out, biases_out)
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=tf_train_labels, logits=logits))
loss += beta * (tf.nn.l2_loss(weights_hidden) + tf.nn.l2_loss(weights_out))
# Optimizer.
optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss)
# Predictions for the training, validation, and test data.
train_prediction = tf.nn.softmax(logits)
#valid_prediction = tf.nn.softmax(tf.matmul(tf_valid_dataset, weights_out) + biases_out)
#test_prediction = tf.nn.softmax(tf.matmul(tf_test_dataset, weights_out) + biases_out)
valid_prediction = tf.nn.softmax(tf.matmul(tf.nn.relu(tf.matmul(tf_valid_dataset, weights_hidden) + biases_hidden), weights_out) + biases_out)
test_prediction = tf.nn.softmax(tf.matmul(tf.nn.relu(tf.matmul(tf_test_dataset, weights_hidden) + biases_hidden), weights_out) + biases_out)
num_steps = 10000
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)
#offset = (step * batch_size) % (3*128 - batch_size)
#print(offset)
# 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))
我认为有两件事会导致这个问题 首先,我不建议在第一层中使用辍学(如果必须的话,使用较低的50%,在10-25%的范围内),因为当你使用如此高的辍学率时,甚至更高级别的特征也不会被学习并传播到更深的层。还可以尝试从10%到50%的辍学率范围,看看准确度是如何变化的。没有办法事先知道什么价值会起作用
第二,在推理时通常不使用辍学。要修复传入,请将dropout的_prob参数保留为占位符,并在推断时将其设置为1
此外,如果您声明的精度值是训练精度,那么首先可能没有太大问题,因为辍学通常会少量降低训练精度,因为您没有过度拟合,需要密切监控的是测试/验证精度您需要在推理过程中关闭辍学。一开始可能不明显,但在NN体系结构中,辍学是硬编码的,这意味着它将在推理过程中影响测试数据。您可以通过创建占位符
keep_prob
来避免这种情况,而不是直接提供值0.5
。例如:
keep_prob = tf.placeholder(tf.float32)
logits = tf.nn.dropout(logits, keep_prob)
要在培训期间启用辍学,请将keep_prob
值设置为0.5:
feed_dict = {tf_train_dataset : batch_data, tf_train_labels : batch_labels, keep_prob: 0.5}
在推断/评估期间,您应该能够执行类似操作,将eval
中的keep_prob
设置为1.0:
accuracy.eval(feed_dict={x: test_prediction, y_: test_labels, keep_prob: 1.0}
编辑:
由于问题似乎不是在推断时使用辍学,下一个罪魁祸首是辍学率对于这个网络规模来说太高。您可以尝试将辍学率降低到20%(即keep_prob=0.8),或增加网络的大小,以使模型有机会学习表示
事实上,我用你的代码试了一下,在这样的网络规模下,我大约有93.5%的人辍学,20%的人辍学。我在下面添加了一些额外的资源,包括最初的辍学论文,以帮助澄清其背后的直觉,并在使用辍学时扩展了更多提示,例如提高学习率
参考资料:
- :有一个使用MNIST的关于上述(辍学开/关)的示例