![](/img/trans.png)
[英]Nans Being Generated after training a neural network for sometime using tensorflow
[英]Tensorflow neural network is always 50% sure after training
我剛剛遵循了有關神經網絡的教程,並試圖將自己的知識用於測試。 我制作了一個簡單的XOR邏輯學習網絡,但由於某種原因,它總是返回0.5
(確定0.5
50%)。 這是我的代碼:
import tensorflow as tf
import numpy as np
def random_normal(shape=1):
return (np.random.random(shape) - 0.5) * 2
train_x = np.array([[1, 0], [0, 1], [1, 1], [0, 0]])
train_y = np.array([1, 1, 0, 0])
input_size = 2
hidden_size = 16
output_size = 1
x = tf.placeholder(dtype=tf.float32, name="X")
y = tf.placeholder(dtype=tf.float32, name="Y")
W1 = tf.Variable(random_normal((input_size, hidden_size)), dtype=tf.float32, name="W1")
W2 = tf.Variable(random_normal((hidden_size, output_size)), dtype=tf.float32, name="W2")
b1 = tf.Variable(random_normal(hidden_size), dtype=tf.float32, name="b1")
b2 = tf.Variable(random_normal(output_size), dtype=tf.float32, name="b2")
l1 = tf.sigmoid(tf.add(tf.matmul(x, W1), b1), name="l1")
result = tf.sigmoid(tf.add(tf.matmul(l1, W2), b2), name="l2")
r_squared = tf.square(result - y)
loss = tf.reduce_mean(r_squared)
optimizer = tf.train.GradientDescentOptimizer(0.1)
train = optimizer.minimize(loss)
hm_epochs = 10000
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for itr in range(hm_epochs):
sess.run(train, {x: train_x, y: train_y})
if itr % 100 == 0:
print("Epoch {} done".format(itr))
print(sess.run(result, {x: [[1, 0]]}))
抱歉,如果這是一個不好的問題,我是機器學習的新手。
您的神經網絡實際上是正確的,答案可能會讓您感到驚訝。 更改...
train_x = np.array([[1, 0], [0, 1], [1, 1], [0, 0]])
train_y = np.array([1, 1, 0, 0])
至...
train_x = np.array([[1, 0], [0, 1], [1, 1], [0, 0]]).reshape((4, 2))
train_y = np.array([1, 1, 0, 0]).reshape((4, 1))
您可以檢查np.array([1, 1, 0, 0]).shape
是(4,)
,不是(4, 1)
。 結果, y
的形狀也變為(4,)
,因此result - y
的形狀為(4, 4)
! 換句話說,損失計算的16個差異與預測和標簽的實際比較無關 。 因此,我對未來的建議是:始終明確指定占位符的形狀,以便更輕松地發現這些錯誤。
您可以在我創建的GitHub gist中找到完整的代碼。 還有一點要注意:最后一個S形實際上使學習[0, 1]
輸出變得更加困難 。 如果刪除它,則網絡收斂速度會更快。
import tensorflow as tf
import keras
import numpy as np
seed = 128
train_x = np.array([[1, 0], [0, 1], [1, 1], [0, 0]])
train_y = np.array([1, 1, 0, 0])
test_x = np.array([[1, 0], [0, 1], [1, 1], [0, 0]])
test_y = np.array([1, 1, 0, 0])
num_classes = 2
y_train_binary = keras.utils.to_categorical(train_y, num_classes)
y_test_binary = keras.utils.to_categorical(test_y, num_classes)
def random_normal(shape=1):
return (np.random.random(shape) - 0.5) * 2
n_hidden_1 = 16
n_input = train_x.shape[1]
n_classes = y_train_binary.shape[1]
weights = {
'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
'out': tf.Variable(tf.random_normal([n_hidden_1, n_classes]))
}
biases = {
'b1': tf.Variable(tf.random_normal([n_hidden_1])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
keep_prob = tf.placeholder("float")
training_epochs = 500
display_step = 100
batch_size = 1
x = tf.placeholder("float", [None, n_input])
y = tf.placeholder("float", [None, n_classes])
def multilayer_perceptron(x, weights, biases):
layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1'])
layer_1 = tf.nn.relu(layer_1)
out_layer = tf.matmul(layer_1, weights['out']) + biases['out']
return out_layer
predictions = multilayer_perceptron(x, weights, biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=predictions, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=0.1).minimize(cost)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
for epoch in range(training_epochs):
avg_cost = 0.0
total_batch = int(len(train_x) / batch_size)
x_batches = np.array_split(train_x, total_batch)
y_batches = np.array_split(y_train_binary, total_batch)
for i in range(total_batch):
batch_x, batch_y = x_batches[i], y_batches[i]
_, c = sess.run([optimizer, cost],
feed_dict={x: batch_x, y: batch_y})
avg_cost += c / total_batch
if epoch % display_step == 0:
print("Epoch:", '%04d' % (epoch+1), "cost={:.9f}".format(avg_cost))
print("Optimization Finished!")
correct_prediction = tf.equal(tf.argmax(predictions, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print("Accuracy:", accuracy.eval({x: test_x, y: y_test_binary}, session=sess))
紀元:0001費用= 3.069790050
紀元:0101費用= 0.001279908
紀元:0201費用= 0.000363608
紀元:0301費用= 0.000168160
紀元:0401費用= 0.000095065
優化完成!
准確度:1.0
test_input = [0, 1]
'Label: ', np.argmax(sess.run(predictions , feed_dict={ x:[test_input]}))
(“標簽:”,1)
對於這種簡單的情況,您可以使用Keras快速測試並查看數據集是否非常適合神經網絡。 但是,您將需要模擬更多數據以充分調整網絡。 我認為梯度下降算法僅使用4個實例的反向傳播就無法找到最佳點。
讓我們模擬更多數據
n = 1000
X_train = np.zeros((n, 2))
y_train = np.zeros((n,))
X_test = np.zeros((n//3, 2))
y_test = np.zeros((n//3,))
for i in range(n):
if n%3 == 0:
a, b = np.random.randint(0,2), np.random.randint(0,2)
X_test[i, 0], X_test[i, 1] = a, b
y_test[i] = (a and not b) or (not a and b)
a, b = np.random.randint(0,2), np.random.randint(0,2)
X_train[i, 0], X_train[i, 1] = a, b
y_train[i] = (a and not b) or (not a and b)
num_classes = 2
y_train_binary = keras.utils.to_categorical(y_train, num_classes)
y_test_binary = keras.utils.to_categorical(y_test, num_classes)
input_shape = (2,)
現在讓我們建立模型
model = Sequential()
model.add(Dense(16, activation='relu',input_shape=input_shape))
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['acc'])
history=model.fit(X_train,
y_train_binary,
epochs=10,
batch_size=8,
validation_data=(X_test, y_test_binary))
這將導致100%的准確性。
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.