InvalidArgumentError:您必须使用dtype float和shape

时间:2019-04-10 08:31:22

标签: python tensorflow deep-learning pycharm

我在我的Pycharm中编写了以下代码,该代码在Tensorflow中执行完全连接层(FCL)。占位符发生无效的参数错误。因此,我在占位符中输入了所有dtypeshapename,但仍然收到无效的参数错误

我想通过FCL模型制作新的Signal(1,222)。
输入信号(1,222)=>输出信号(1,222)

  • maxPredict:在输出信号中找到具有最高值的索引。
  • calculate Y:获取与maxPredict相对应的频率数组值。
  • loss:使用真实Y之间的差并将Y计算为损失。
  • loss = tf.abs(trueY -calculateY)`

代码(发生错误)
x = tf.placeholder(dtype=tf.float32, shape=[1, 222], name='inputX')

错误

  

InvalidArgumentError(请参见上面的回溯):您必须使用dtype float和shape [1,222]输入占位符张量“ inputX”的值   tensorflow.python.framework.errors_impl.InvalidArgumentError:您必须使用dtype float和shape [1,222]输入占位符张量“ inputX”的值        [[{{node inputX}} = Placeholderdtype = DT_FLOAT,shape = [1,222],_ device =“ / job:localhost /副本:0 / task:0 / device:CPU:0”]]   在处理上述异常期间,发生了另一个异常:

新的错误案例

我更改了密码。
x = tf.placeholder(tf.float32, [None, 222], name='inputX')

错误案例1
tensorFreq = tf.convert_to_tensor(basicFreq, tf.float32)
newY = tf.gather(tensorFreq, maxPredict) * 60
loss = tf.abs(y - tf.Variable(newY))

  

ValueError:initial_value必须具有指定的形状:Tensor(“ mul:0”,shape =(?,),dtype = float32)

错误案例2
tensorFreq = tf.convert_to_tensor(basicFreq, tf.float32)
newY = tf.gather(tensorFreq, maxPredict) * 60
loss = tf.abs(y - newY)

  

回溯(最近通话最近):     文件“ D:/PycharmProject/DetectionSignal/TEST_FCL_StackOverflow.py”,第127行,在       trainStep = opt.minimize(损失)     最小的文件“ C:\ Users \ Heewony \ Anaconda3 \ envs \ TSFW_pycharm \ lib \ site-packages \ tensorflow \ python \ training \ optimizer.py”,第407行       ([_的str(v),grads_and_vars中的v,损失))   ValueError:没有为任何变量提供渐变,请在变量[tf.Variable'Variable:0'shape =(222,1024)dtype = float32_ref,tf之间检查是否有不支持渐变的操作 .variable'Variable_1:0'shape =(1024,)dtype = float32_re,......... tf.variable'Variable_5:0'shape =(222,)dtype = float32_ref]和损失张量(“ Abs:0”,dtype = float32)

开发环境

  • OS平台和发行版:Windows 10 x64
  • 从以下位置安装的TensorFlow:Anaconda
  • Tensorflow版本1.12.0:
  • python 3.6.7:
  • 移动设备:不适用
  • 要复制的精确命令:N / A
  • GPU型号和内存:NVIDIA GeForce CTX 1080 Ti
  • CUDA / cuDNN:9.0 / 7.4

型号和功能

def Model_FCL(inputX):
    data = inputX  # input Signals

    # Fully Connected Layer 1
    flatConvh1 = tf.reshape(data, [-1, 222])
    fcW1 = tf.Variable(tf.truncated_normal(shape=[222, 1024], stddev=0.05))
    fcb1 = tf.Variable(tf.constant(0.1, shape=[1024]))
    fch1 = tf.nn.relu(tf.matmul(flatConvh1, fcW1) + fcb1)

    # Fully Connected Layer 2
    flatConvh2 = tf.reshape(fch1, [-1, 1024])
    fcW2 = tf.Variable(tf.truncated_normal(shape=[1024, 1024], stddev=0.05))
    fcb2 = tf.Variable(tf.constant(0.1, shape=[1024]))
    fch2 = tf.nn.relu(tf.matmul(flatConvh2, fcW2) + fcb2)

    # Output Layer
    fcW3 = tf.Variable(tf.truncated_normal(shape=[1024, 222], stddev=0.05))
    fcb3 = tf.Variable(tf.constant(0.1, shape=[222]))

    logits = tf.add(tf.matmul(fch2, fcW3), fcb3)
    predictY = tf.nn.softmax(logits)
    return predictY, logits

def loadMatlabData(fileName):
    contentsMat = sio.loadmat(fileName)
    dataInput = contentsMat['dataInput']
    dataLabel = contentsMat['dataLabel']

    dataSize = dataInput.shape
    dataSize = dataSize[0]
    return dataInput, dataLabel, dataSize

def getNextSignal(num, data, labels, WINDOW_SIZE, OUTPUT_SIZE):
    shuffleSignal = data[num]
    shuffleLabels = labels[num]

    # shuffleSignal = shuffleSignal.reshape(1, WINDOW_SIZE)
    # shuffleSignal = np.asarray(shuffleSignal, np.float32)
    return shuffleSignal, shuffleLabels

def getBasicFrequency():
    # basicFreq => shape(222)
    basicFreq = np.array([0.598436736688, 0.610649731314, ... 3.297508549096])
    return basicFreq

图表

basicFreq = getBasicFrequency()
myGraph = tf.Graph()
with myGraph.as_default():
    # define input data & output data 입력받기 위한 placeholder
    x = tf.placeholder(dtype=tf.float32, shape=[1, 222], name='inputX') # Signal size = [1, 222]
    y = tf.placeholder(tf.float32, name='trueY') # Float value size = [1]

    print('inputzz ', x, y)
    print('Graph  ', myGraph.get_operations())
    print('TrainVariable ', tf.trainable_variables())

    predictY, logits = Model_FCL(x) # Predict Signal, size = [1, 222]
    maxPredict = tf.argmax(predictY, 1, name='maxPredict') # Find max index of Predict Signal

    tensorFreq = tf.convert_to_tensor(basicFreq, tf.float32)
    newY = tf.gather(tensorFreq, maxPredict) * 60   # Find the value that corresponds to the Freq array index
    loss = tf.abs(y - tf.Variable(newY))  # Calculate absolute (true Y - predict Y)
    opt = tf.train.AdamOptimizer(learning_rate=0.0001)
    trainStep = opt.minimize(loss)

    print('Graph  ', myGraph.get_operations())
    print('TrainVariable ', tf.trainable_variables())  

会话

with tf.Session(graph=myGraph) as sess:
    sess.run(tf.global_variables_initializer())

    dataFolder = './'
    writer = tf.summary.FileWriter('./logMyGraph', sess.graph)
    startTime = datetime.datetime.now()

    numberSummary = 0
    accuracyTotalTrain = []
    for trainEpoch in range(1, 25 + 1):
        arrayTrain = []

        dataPPG, dataLabel, dataSize = loadMatlabData(dataFolder + "TestValues.mat")

        for i in range(dataSize):
            batchSignal, valueTrue = getNextSignal(i, dataPPG, dataLabel, 222, 222)
            _, lossPrint, valuePredict = sess.run([trainStep, loss, newY], feed_dict={x: batchSignal, y: valueTrue})
            print('Train ', i, ' ', valueTrue, ' - ', valuePredict, '   Loss ', lossPrint)

            arrayTrain.append(lossPrint)
            writer.add_summary(tf.Summary(value=[tf.Summary.Value(tag='Loss', simple_value=float(lossPrint))]),
                               numberSummary)
            numberSummary += 1
        accuracyTotalTrain.append(np.mean(arrayTrain))
    print('Final Train : ', accuracyTotalTrain)

    sess.close()    

2 个答案:

答案 0 :(得分:0)

似乎变量batchSignal的类型或形状错误。它必须是一个形状完全为[1, 222]的numpy数组。如果要使用批量 n ×222的示例,占位符x的形状应为[None, 222],占位符y的形状应为{{1 }}。

顺便说一句,考虑使用tf.layers.dense而不是显式初始化变量并自己实现层。

答案 1 :(得分:0)

应该改变两件事。

错误案例0。您无需重新调整图层之间的流程。您可以在第一个维度上使用None来传递动态批量大小。

错误情况1。您可以直接将newY用作NN的输出。您只能使用tf.Variable定义权重或偏差。

错误情况2。看来,tf.abs()tf.gather()都没有tensorflow实现梯度下降。对于回归问题,均方误差通常就足够了。

在这里,我如何重写您的代码。我没有您的matlab部分,因此无法调试您的python / matlab接口:

型号:

def Model_FCL(inputX):
    # Fully Connected Layer 1
    fcW1 = tf.get_variable('w1', shape=[222, 1024], initializer=tf.initializer.truncated_normal())
    fcb1 = tf.get_variable('b1', shape=[222], initializer=tf.initializer.truncated_normal())
    # fcb1 = tf.get_variable('b1', shape=[None, 222], trainable=False, initializer=tf.constant_initializer(valueThatYouWant)) # if you want to fix your bias constant
    fch1 = tf.nn.relu(tf.matmul(inputX, fcW1) + fcb1, name='relu1')

    # Fully Connected Layer 2
    fcW2 = tf.get_variable('w2', shape=[1024, 1024], initializer=tf.initializer.truncated_normal())
    fcb2 = tf.get_variable('b2', shape=[222], initializer=tf.initializer.truncated_normal())
    # fcb2 = tf.get_variable('b2', shape=[None, 222], trainable=False, initializer=tf.constant_initializer(valueThatYouWant)) # if you want to fix your bias constant
    fch2 = tf.nn.relu(tf.matmul(fch1, fcW2) + fcb2, name='relu2')

    # Output Layer
    fcW3 = tf.get_variable('w3', shape=[1024, 222], initializer=tf.initializer.truncated_normal())
    fcb3 = tf.get_variable('b3', shape=[222], initializer=tf.initializer.truncated_normal())
    # fcb2 = tf.get_variable('b2', shape=[None, 222], trainable=False, initializer=tf.constant_initializer(valueThatYouWant)) # if you want to fix your bias constant
    logits = tf.add(tf.matmul(fch2, fcW3), fcb3)

    predictY = tf.nn.softmax(logits)  #I'm not sure that it will learn if you do softmax then abs/MSE
    return predictY, logits

图形:

with myGraph.as_default():
    # define input data & output data 입력받기 위한 placeholder
    # put None(dynamic batch size) not -1 at the first dimension so that you can change your batch size
    x = tf.placeholder(tf.float32, shape=[None, 222], name='inputX')  # Signal size = [1, 222]
    y = tf.placeholder(tf.float32, shape=[None], name='trueY')  # Float value size = [1]

    ...

    predictY, logits = Model_FCL(x)  # Predict Signal, size = [1, 222]
    maxPredict = tf.argmax(predictY, 1, name='maxPredict')  # Find max index of Predict Signal

    tensorFreq = tf.convert_to_tensor(basicFreq, tf.float32)
    newY = tf.gather(tensorFreq, maxPredict) * 60   # Find the value that corresponds to the Freq array index

    loss = tf.losses.mean_squared_error(labels=y, predictions=newY)  # maybe use MSE for regression problem
    # loss = tf.abs(y - newY)  # Calculate absolute (true Y - predict Y) #tensorflow doesn't have gradient descent implementation for tf.abs
    opt = tf.train.AdamOptimizer(learning_rate=0.0001)
    trainStep = opt.minimize(loss)