Python 张量流模型的求解精度
我尝试在使用sigmoid函数训练这个简单的线性模型后找到精度:Python 张量流模型的求解精度,python,tensorflow,tensorflow-estimator,Python,Tensorflow,Tensorflow Estimator,我尝试在使用sigmoid函数训练这个简单的线性模型后找到精度: import numpy as np import tensorflow as tf import _pickle as cPickle with open("var_x.txt", "rb") as fp: # Unpickling var_x = cPickle.load(fp) with open("var_y.txt", "rb") as fp: # Unpickling var_y = cPi
import numpy as np
import tensorflow as tf
import _pickle as cPickle
with open("var_x.txt", "rb") as fp: # Unpickling
var_x = cPickle.load(fp)
with open("var_y.txt", "rb") as fp: # Unpickling
var_y = cPickle.load(fp)
with open("var_x_test.txt", "rb") as fp: # Unpickling
var_x_test = cPickle.load(fp)
with open("var_y_test.txt", "rb") as fp: # Unpickling
var_y_test = cPickle.load(fp)
def model_fn(features, labels, mode):
# Build a linear model and predict values
W = tf.get_variable("W", [4], dtype=tf.float64)
b = tf.get_variable("b", [1], dtype=tf.float64)
y = tf.sigmoid( tf.reduce_sum(W*features['x']) + b)
if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(mode=mode, predictions=y)
loss = tf.reduce_sum(tf.square(y - labels))
global_step = tf.train.get_global_step()
optimizer = tf.train.GradientDescentOptimizer(0.01)
train = tf.group(optimizer.minimize(loss),
tf.assign_add(global_step, 1))
return tf.estimator.EstimatorSpec(
mode=mode,
predictions=y,
loss=loss,
train_op=train)
estimator = tf.estimator.Estimator(model_fn=model_fn)
x_train = np.array(var_x)
y_train = np.array(var_y)
x_test = np.array(var_x_test)
y_test = np.array(var_y_test)
input_fn = tf.estimator.inputs.numpy_input_fn(
{"x": x_train}, y_train, batch_size=4, num_epochs=60, shuffle=True)
estimator.train(input_fn=input_fn, steps=1000)
test_input_fn= tf.estimator.inputs.numpy_input_fn(
x ={"x":np.array(x_test)},
y=np.array(y_test),
num_epochs=1,
shuffle=False
)
accuracy_score = estimator.evaluate(input_fn=test_input_fn["accuracy"])
print(accuracy_score)
但这本词典没有“准确性”的关键。我怎么找到它?此外,我如何使用tensorboard跟踪每一步后的精度
提前感谢您,tensorflow教程在解释方面非常糟糕
accuracy_score = estimator.evaluate(input_fn=test_input_fn)
print(accuracy_score["loss"])
您可以像上述方法一样获得损失以获得准确度。您需要使用在
模型中自己创建准确度fn
并将其传递给函数将返回的评估度量操作
def型号(功能、标签、模式):
#定义模型。。。
y=tf.nn.sigmoid(…)
预测=tf.cast(y>0.5,tf.int64)
eval_metric_ops={'accurity':tf.metrics.accurity(标签、预测)}
#...
返回tf.estimator.EstimatorSpec(模式=模式,列车运行=列车运行,
损失=损失,评估度量操作=评估度量操作)
然后,estimator.evaluate()
的输出将包含一个精度键,该键将保存在验证集上计算的精度
metrics=估计器。评估(测试输入)
打印(指标[‘准确度’])
不起作用,字典没有关键的“准确性”。我照你说的做了,但它抛出了错误“NameError:名称‘预测’未定义”。你必须自己这样定义:tf.argmax(y,axis=1)
在你的情况下,你应该使用predictions=tf.cast(y>0.5,tf.int64)
对不起(当sigmoid的输出大于0.5时预测1)。我已更新了答案。链接已断开,正确的答案是这个吗?仅代码答案没有特别帮助。请简要说明此代码如何解决问题。
test_results = {}
test_results['model'] = model.evaluate(
test_features, test_labels, verbose=0)
print(f" Accuracy: {test_results}")