我刚刚写完了我的第一个神经网络,它终于有效了,但它确实很糟糕。我的准确度大约为0.37。有关如何使其更准确的任何提示?我已经尝试过不同的学习率和不同数量的隐藏层单元,但我的精确度从未超过0.37。我正在尝试将数据分类为3个类0,1或2中的一个。我使用1个热矩阵作为我的Y.我怎样才能改进我的代码?
X = data[1:, 2:]
m, n = X.shape
labels = data[1:, 1]
Y = np.zeros((m,3))
i = 0
for label in labels:
if label == 0:
Y[i,0] = 1
elif label == 1:
Y[i,1] = 1
elif label == 2:
Y[i,2] = 1
i += 1
slice_size = math.floor(m/5)
X_test = X[-slice_size:, :]
Y_test = Y[-slice_size:]
X_train = X[:slice_size, :]
Y_train = Y[:slice_size]
learning_rate = 0.00001
num_steps = 200
batch_size = 100
display_step = 2
n_nodes_hl1 = 5
n_nodes_hl2 = 5
n_nodes_hl3 = 5
n_classes = 3
n_inputs = 16
training_epochs = 500
x = tf.placeholder('float32', [None,n])
y = tf.placeholder('float32', [None, n_classes])
weights = {
'h1': tf.Variable(tf.random_normal([n_inputs, n_nodes_hl1])),
'h2': tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
'h3': tf.Variable(tf.random_normal([n_nodes_hl2, n_nodes_hl3])),
'out': tf.Variable(tf.random_normal([n_nodes_hl1, n_classes]))
}
biases = {
'b1': tf.Variable(tf.random_normal([n_nodes_hl1])),
'b2': tf.Variable(tf.random_normal([n_nodes_hl2])),
'b3': tf.Variable(tf.random_normal([n_nodes_hl3])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
def neural_network(data):
layer_1 = tf.add(tf.matmul(data, weights['h1']), biases['b1'])
layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
layer_3 = tf.add(tf.matmul(layer_2, weights['h3']), biases['b3'])
output = tf.matmul(layer_3, weights['out']) + biases['out']
return output
logits = neural_network(x)
prediction = tf.nn.softmax(logits)
loss_op =
tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=logits,
labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
train_op = optimizer.minimize(loss_op)
correct_pred = tf.equal(tf.argmax(prediction, 1), tf.argmax(Y_train, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initialize the variables (i.e. assign their default value)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for step in range(1, num_steps+1):
x_step = np.asarray(X_train[step,:])
y_step = np.asarray(Y_train[step])
x_step = np.reshape(x_step, (1, n))
y_step = np.reshape(y_step, (1,n_classes))
sess.run(train_op, feed_dict={x:x_step , y:y_step})
if step % display_step == 0 or step == 1:
#Calculate batch loss and accuracy
loss, acc = sess.run([loss_op, accuracy], feed_dict={x: x_step,
y: y_step})
print("Step " + str(step) + ", Minibatch Loss= " +
"{:.4f}".format(loss) + ", Training Accuracy= " +
"{:.3f}".format(acc))
x_step_test = np.asarray(X_test)
y_step_test = np.asarray(Y_test)
x_step_test = np.reshape(x_step, (1, n))
y_step_test = np.reshape(y_step, (1,n_classes))
print("Optimization Finished!")
print("Testing Accuracy:",
sess.run(accuracy, feed_dict={x: x_step_test,
y: y_step_test}))
答案 0 :(得分:0)
1
x_step_test = np.asarray(X_test)
y_step_test = np.asarray(Y_test)
x_step_test = np.reshape(x_step, (1, n))
y_step_test = np.reshape(y_step, (1,n_classes))
不应该是:
x_step_test = np.asarray(X_test)
y_step_test = np.asarray(Y_test)
x_step_test = np.reshape(x_step_test, (1, n))
y_step_test = np.reshape(y_step_test, (1,n_classes))
同时检查如何进行批次,可能会有一些问题。
使用train_test_split
中的sklearn.model_selection
,它会在改组后拆分您的火车和测试数据。如果您的数据具有某种模式,那么不改变您的数据可能会产生问题,例如。你有99个数据点,前33个包含它的狗,另外33个包含它的猫,而最后33个它是一个鼠标,你的神经网络只训练66只狗和猫的图像,并且不会学会识别鼠标。
提高学习率,AdamOptimizer已经衰减lr,使用0.1或0.01之类的东西。
我猜张量流部分是正确的。