tensorflow - 使用 CNN 和 LSTM 在 Tensorflow 中占位符大小和类型的错误

Question

我使用以下代码结合了 CNN 和 LSTM：

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import itertools

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from scipy import stats
import tensorflow as tf
import pyfftw
from scipy import signal
import xlrd
from tensorflow.python.tools import freeze_graph
from tensorflow.python.tools import optimize_for_inference_lib
import seaborn as sns

from sklearn.metrics import confusion_matrix

##matplotlib inline
plt.style.use('ggplot')


## define funtions
def read_data(file_path):
##    column_names = ['user-id','activity','timestamp', 'x-axis', 'y-axis', 'z-axis']
    column_names = ['activity','timestamp', 'Ax', 'Ay', 'Az', 'Lx', 'Ly', 'Lz', 'Gx', 'Gy', 'Gz', 'Mx', 'My', 'Mz'] ## 3 sensors
    data = pd.read_csv(file_path,header = None, names = column_names)
    return data

def feature_normalize(dataset):
    mu = np.mean(dataset,axis = 0)
    sigma = np.std(dataset,axis = 0)
    return (dataset - mu)/sigma

def plot_axis(ax, x, y, title):
    ax.plot(x, y)
    ax.set_title(title)
    ax.xaxis.set_visible(False)
    ax.set_ylim([min(y) - np.std(y), max(y) + np.std(y)])
    ax.set_xlim([min(x), max(x)])
    ax.grid(True)

def plot_activity(activity,data):
    fig, (ax0, ax1, ax2) = plt.subplots(nrows = 3, figsize = (15, 10), sharex = True)
    plot_axis(ax0, data['timestamp'], data['Ax'], 'x-axis')
    plot_axis(ax1, data['timestamp'], data['Ay'], 'y-axis')
    plot_axis(ax2, data['timestamp'], data['Az'], 'z-axis')
    plt.subplots_adjust(hspace=0.2)
    fig.suptitle(activity)
    plt.subplots_adjust(top=0.90)
    plt.show()

def windows(data, size):
    start = 0
    while start < data.count():
        yield start, start + size
        start += (size / 2)

def segment_signal(data, window_size = None, num_channels=None): # edited
    segments = np.empty((0,window_size,num_channels)) #change from 3 to 9 channels for AGM fusion #use variable num_channels=9
    labels = np.empty((0))
    for (n_start, n_end) in windows(data['timestamp'], window_size):
##        x = data["x-axis"][start:end]
##        y = data["y-axis"][start:end]
##        z = data["z-axis"][start:end]
        n_start = int(n_start)
        n_end = int(n_end)
        Ax = data["Ax"][n_start:n_end]
        Ay = data["Ay"][n_start:n_end]
        Az = data["Az"][n_start:n_end]
        Lx = data["Lx"][n_start:n_end]
        Ly = data["Ly"][n_start:n_end]
        Lz = data["Lz"][n_start:n_end]
        Gx = data["Gx"][n_start:n_end]
        Gy = data["Gy"][n_start:n_end]
        Gz = data["Gz"][n_start:n_end]
        Mx = data["Mx"][n_start:n_end]
        My = data["My"][n_start:n_end]
        Mz = data["Mz"][n_start:n_end]
        if(len(data['timestamp'][n_start:n_end]) == window_size): # include only windows with size of 90
            segments = np.vstack([segments,np.dstack([Ax,Ay,Az,Gx,Gy,Gz,Mx,My,Mz])])
            labels = np.append(labels,stats.mode(data["activity"][n_start:n_end])[0][0])
    return segments, labels

def weight_variable(shape, restore_name):
    initial = tf.truncated_normal(shape, stddev = 0.1)
    return tf.Variable(initial, name=restore_name)

def bias_variable(shape, restore_name):
    initial = tf.constant(0.0, shape = shape)
    return tf.Variable(initial, name=restore_name)

def depthwise_conv2d(x, W):
    return tf.nn.depthwise_conv2d(x,W, [1, 1, 1, 1], padding='VALID')

def apply_depthwise_conv(x,weights,biases):
    return tf.nn.relu(tf.add(depthwise_conv2d(x, weights),biases))

def apply_max_pool(x,kernel_size,stride_size):
    return tf.nn.max_pool(x, ksize=[1, 1, kernel_size, 1], 
                          strides=[1, 1, stride_size, 1], padding='VALID') 

#------------------------get dataset----------------------#

## run shoaib_dataset.py to generate dataset_shoaib_total.txt

## get data from dataset_shoaib_total.txt
dataset_belt = read_data('dataset_shoaibsensoractivity_participant_belt.txt')
dataset_left_pocket = read_data('dataset_shoaibsensoractivity_participant_left_pocket.txt')
dataset_right_pocket = read_data('dataset_shoaibsensoractivity_participant_right_pocket.txt')
dataset_upper_arm = read_data('dataset_shoaibsensoractivity_participant_upper_arm.txt')
dataset_wrist = read_data('dataset_shoaibsensoractivity_participant_wrist.txt')



#--------------------preprocessing------------------------#

dataset_belt['Ax'] = feature_normalize(dataset_belt['Ax'])
dataset_belt['Ay'] = feature_normalize(dataset_belt['Ay'])
dataset_belt['Az'] = feature_normalize(dataset_belt['Az'])
dataset_belt['Gx'] = feature_normalize(dataset_belt['Gx'])
dataset_belt['Gy'] = feature_normalize(dataset_belt['Gy'])
dataset_belt['Gz'] = feature_normalize(dataset_belt['Gz'])
dataset_belt['Mx'] = feature_normalize(dataset_belt['Mx'])
dataset_belt['My'] = feature_normalize(dataset_belt['My'])
dataset_belt['Mz'] = feature_normalize(dataset_belt['Mz'])

dataset_left_pocket['Ax'] = feature_normalize(dataset_left_pocket['Ax'])
dataset_left_pocket['Ay'] = feature_normalize(dataset_left_pocket['Ay'])
dataset_left_pocket['Az'] = feature_normalize(dataset_left_pocket['Az'])
dataset_left_pocket['Gx'] = feature_normalize(dataset_left_pocket['Gx'])
dataset_left_pocket['Gy'] = feature_normalize(dataset_left_pocket['Gy'])
dataset_left_pocket['Gz'] = feature_normalize(dataset_left_pocket['Gz'])
dataset_left_pocket['Mx'] = feature_normalize(dataset_left_pocket['Mx'])
dataset_left_pocket['My'] = feature_normalize(dataset_left_pocket['My'])
dataset_left_pocket['Mz'] = feature_normalize(dataset_left_pocket['Mz'])

dataset_right_pocket['Ax'] = feature_normalize(dataset_right_pocket['Ax'])
dataset_right_pocket['Ay'] = feature_normalize(dataset_right_pocket['Ay'])
dataset_right_pocket['Az'] = feature_normalize(dataset_right_pocket['Az'])
dataset_right_pocket['Gx'] = feature_normalize(dataset_right_pocket['Gx'])
dataset_right_pocket['Gy'] = feature_normalize(dataset_right_pocket['Gy'])
dataset_right_pocket['Gz'] = feature_normalize(dataset_right_pocket['Gz'])
dataset_right_pocket['Mx'] = feature_normalize(dataset_right_pocket['Mx'])
dataset_right_pocket['My'] = feature_normalize(dataset_right_pocket['My'])
dataset_right_pocket['Mz'] = feature_normalize(dataset_right_pocket['Mz'])

dataset_upper_arm['Ax'] = feature_normalize(dataset_upper_arm['Ax'])
dataset_upper_arm['Ay'] = feature_normalize(dataset_upper_arm['Ay'])
dataset_upper_arm['Az'] = feature_normalize(dataset_upper_arm['Az'])
dataset_upper_arm['Gx'] = feature_normalize(dataset_upper_arm['Gx'])
dataset_upper_arm['Gy'] = feature_normalize(dataset_upper_arm['Gy'])
dataset_upper_arm['Gz'] = feature_normalize(dataset_upper_arm['Gz'])
dataset_upper_arm['Mx'] = feature_normalize(dataset_upper_arm['Mx'])
dataset_upper_arm['My'] = feature_normalize(dataset_upper_arm['My'])
dataset_upper_arm['Mz'] = feature_normalize(dataset_upper_arm['Mz'])


dataset_wrist['Ax'] = feature_normalize(dataset_wrist['Ax'])
dataset_wrist['Ay'] = feature_normalize(dataset_wrist['Ay'])
dataset_wrist['Az'] = feature_normalize(dataset_wrist['Az'])
dataset_wrist['Gx'] = feature_normalize(dataset_wrist['Gx'])
dataset_wrist['Gy'] = feature_normalize(dataset_wrist['Gy'])
dataset_wrist['Gz'] = feature_normalize(dataset_wrist['Gz'])
dataset_wrist['Mx'] = feature_normalize(dataset_wrist['Mx'])
dataset_wrist['My'] = feature_normalize(dataset_wrist['My'])
dataset_wrist['Mz'] = feature_normalize(dataset_wrist['Mz'])


#------------------fixed hyperparameters--------------------#

window_size = 200 #from 90 #FIXED at 4 seconds


#----------------input hyperparameters------------------#

input_height = 1
input_width = window_size
num_labels = 7
num_channels = 9 #from 3 channels #9 channels for AGM


#-------------------sliding time window----------------#

segments_belt, labels_belt = segment_signal(dataset_belt, window_size=window_size, num_channels=num_channels)
labels_belt = np.asarray(pd.get_dummies(labels_belt), dtype = np.int8)
reshaped_segments_belt = segments_belt.reshape(len(segments_belt), (window_size*num_channels)) #use variable num_channels instead of constant 3 channels

segments_left_pocket, labels_left_pocket = segment_signal(dataset_left_pocket, window_size=window_size, num_channels=num_channels)
labels_left_pocket = np.asarray(pd.get_dummies(labels_left_pocket), dtype = np.int8)
reshaped_segments_left_pocket = segments_left_pocket.reshape(len(segments_left_pocket), (window_size*num_channels)) #use variable num_channels instead of constant 3 channels

segments_right_pocket, labels_right_pocket = segment_signal(dataset_right_pocket, window_size=window_size, num_channels=num_channels)
labels_right_pocket = np.asarray(pd.get_dummies(labels_right_pocket), dtype = np.int8)
reshaped_segments_right_pocket = segments_right_pocket.reshape(len(segments_right_pocket), (window_size*num_channels)) #use variable num_channels instead of constant 3 channels

segments_upper_arm, labels_upper_arm = segment_signal(dataset_upper_arm, window_size=window_size, num_channels=num_channels)
labels_upper_arm = np.asarray(pd.get_dummies(labels_upper_arm), dtype = np.int8)
reshaped_segments_upper_arm = segments_upper_arm.reshape(len(segments_upper_arm), (window_size*num_channels)) #use variable num_channels instead of constant 3 channels

segments_wrist, labels_wrist = segment_signal(dataset_wrist, window_size=window_size, num_channels=num_channels)
labels_wrist = np.asarray(pd.get_dummies(labels_wrist), dtype = np.int8)
reshaped_segments_wrist = segments_wrist.reshape(len(segments_wrist), (window_size*num_channels)) #use variable num_channels instead of constant 3 channels



##reshaped_segments = np.vstack([reshaped_segments1,reshaped_segments2,reshaped_segments3,reshaped_segments4,reshaped_segments5,reshaped_segments6,reshaped_segments7,reshaped_segments8,reshaped_segments9,reshaped_segments10])
##labels = np.vstack([labels1,labels2,labels3,labels4,labels5,labels6,labels7,labels8,labels9,labels10])



# all locations
reshaped_segments = np.vstack([reshaped_segments_belt,reshaped_segments_left_pocket,reshaped_segments_right_pocket,reshaped_segments_upper_arm,reshaped_segments_wrist])
labels = np.vstack([labels_belt,labels_left_pocket,labels_right_pocket,labels_upper_arm,labels_wrist]) 


#------------divide data into test and training `set-----------#

train_test_split = np.random.rand(len(reshaped_segments)) < 0.70
train_x = reshaped_segments[train_test_split]
train_y = labels[train_test_split]
test_x = reshaped_segments[~train_test_split]
test_y = labels[~train_test_split]



#---------------training hyperparameters----------------#

batch_size = 10
kernel_size = 60 #from 60 #optimal 2
depth = 15 #from 60 #optimal 15
num_hidden = 1000 #from 1000 #optimal 80

learning_rate = 0.0001
training_epochs = 8


total_batches = train_x.shape[0] ##// batch_size # included // batch_size



#---------define placeholders for input----------#

X = tf.placeholder(tf.float32, shape=[None,input_width * num_channels], name="input")
X_reshaped = tf.reshape(X,[-1,input_height,input_width,num_channels])
Y = tf.placeholder(tf.float32, shape=[None,num_labels])


#---------------------perform convolution-----------------#

# first convolutional layer 
c_weights = weight_variable([1, kernel_size, num_channels, depth], restore_name="c_weights")
c_biases = bias_variable([depth * num_channels], restore_name="c_biases")

c = apply_depthwise_conv(X_reshaped,c_weights,c_biases)
p = apply_max_pool(c,20,2)

# second convolutional layer
c2_weights = weight_variable([1, 6,depth*num_channels,depth//10], restore_name="c2_weights")
c2_biases = bias_variable([(depth*num_channels)*(depth//10)], restore_name="c2_biases")

c2 = apply_depthwise_conv(p,c2_weights,c2_biases)


n_classes = 7
n_hidden = 128
n_inputs = 540 # 540 = 60*3 not 180 # or 7*9*10
lstm_size = 128

rnnW = {
    'hidden': tf.Variable(tf.random_normal([n_inputs, n_hidden])),
    'output': tf.Variable(tf.random_normal([n_hidden, n_classes]))
}

rnnBiases = {
    'hidden': tf.Variable(tf.random_normal([n_hidden], mean=1.0)),
    'output': tf.Variable(tf.random_normal([n_classes]))
}

c2Reshape = tf.reshape(c2, [-1, 7, 200])
shuff = tf.transpose(c2Reshape, [1, 0, 2])
shuff = tf.reshape(shuff, [-1, n_inputs])

# Linear activation, reshaping inputs to the LSTM's number of hidden:
hidden = tf.nn.relu(tf.matmul(
    shuff, rnnW['hidden']
) + rnnBiases['hidden'])

# Split the series because the rnn cell needs time_steps features, each of shape:
hidden = tf.split(axis=0, num_or_size_splits=7, value=hidden)

lstm_cell = tf.contrib.rnn.LSTMCell(lstm_size, forget_bias=1.0)
# Stack two LSTM layers, both layers has the same shape
lstm_layers = tf.contrib.rnn.MultiRNNCell([lstm_cell] * 2)

lstmOutputs, _ = tf.contrib.rnn.static_rnn(lstm_layers, hidden, dtype=tf.float32)
lstmLastOutput = lstmOutputs[-1]
y_ = tf.matmul(lstmLastOutput, rnnW['output']) + rnnBiases['output']





#-----------------loss optimization-------------#

loss = -tf.reduce_sum(Y * tf.log(y_))
optimizer = tf.train.GradientDescentOptimizer(learning_rate = learning_rate).minimize(loss)
##optimizer = tf.train.AdamOptimizer(learning_rate = learning_rate).minimize(loss)


#-----------------compute accuracy---------------#

correct_prediction = tf.equal(tf.argmax(y_,1), tf.argmax(Y,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

cost_history = np.empty(shape=[1],dtype=float)
saver = tf.train.Saver()



#-----------------run session--------------------#

session = tf.Session()
session.run(tf.global_variables_initializer())

for epoch in range(8):
    for b in range(total_batches):    
        offset = (b * batch_size) % (train_y.shape[0] - batch_size)
        batch_x = train_x[offset:(offset + batch_size), :]
        batch_y = train_y[offset:(offset + batch_size), :]
        _, c = session.run([optimizer, loss],feed_dict={X: batch_x, Y : batch_y})
        cost_history = np.append(cost_history,c)
    print("Epoch: ",epoch," Training Loss: ",c," Training Accuracy: ",\
            session.run(accuracy, feed_dict={X: train_x, Y: train_y}))

print("Testing Accuracy:", session.run(accuracy, feed_dict={X: test_x, Y: test_y}))

if 1==1:
    print ("Testing Accuracy: ", session.run(accuracy, feed_dict={X: test_x, Y: test_y}),'\n')
    pred_y = session.run(tf.argmax(y_ ,1),feed_dict={X: test_x})
    cm = confusion_matrix(np.argmax(test_y ,1),pred_y)
    print (cm, '\n')
    plt.imshow(cm)
    plt.title('Confusion Matrix')
    plt.rcParams['image.cmap'] = 'afmhot'
    plt.colorbar()
    tick_marks = np.arange(len(['Wal', 'Std', 'Jog', 'Sit', 'Bik', 'Wlu', 'Wld']))
    plt.xticks(tick_marks, ['Wal', 'Std', 'Jog', 'Sit', 'Bik', 'Wlu', 'Wld'])
    plt.yticks(tick_marks, ['Wal', 'Std', 'Jog', 'Sit', 'Bik', 'Wlu', 'Wld'])

    fmt = '.2f'
    thresh = cm.max() / 2.
    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
        plt.text(j, i, format(cm[i, j], fmt),
                 horizontalalignment="center",
                 color="white" if cm[i, j] > thresh else "black")

    plt.tight_layout()
    plt.ylabel('True label')
    plt.xlabel('Predicted label')
    plt.figure()
    plt.show()

但是，我总是收到此错误：

Traceback（最近一次调用最后一次）：文件“C:\Users\Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\client\session.py”，第 1322 行，在 _do_call 返回fn(*args) 文件“C:\Users\Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\client\session.py”，第 1307 行，在 _run_fn 选项中，feed_dict， fetch_list, target_list, run_metadata) 文件“C:\Users\Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\client\session.py”，第 1409 行，在 _call_tf_sessionrun run_metadata) tensorflow .python.framework.errors_impl.InvalidArgumentError：不兼容的形状：[10,7] vs. [20,7] [[Node: mul = Mul[T=DT_FLOAT, _device="/job:localhost/replica:0/task: 0/设备:CPU:0"](_arg_Placeholder_0_0, 日志)]]

在处理上述异常的过程中，又出现了一个异常：

回溯（最后一次调用）：文件“”，第 6 行，在 _，c = session.run([optimizer, loss],feed_dict={X: batch_x, Y: batch_y}) 文件“C:\Users\Charlene \AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\client\session.py"，第 900 行，在运行 run_metadata_ptr) 文件“C:\Users\Charlene\AppData\Local\Programs\ Python\Python35\lib\site-packages\tensorflow\python\client\session.py”，第 1135 行，在 _run feed_dict_tensor、options、run_metadata）文件“C:\Users\Charlene\AppData\Local\Programs\Python\Python35 \lib\site-packages\tensorflow\python\client\session.py"，第 1316 行，在 _do_run run_metadata) 文件“C:\Users\Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\ tensorflow\python\client\session.py"，第 1335 行，在 _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.InvalidArgumentError: 不兼容的形状：[10,7] vs. [20,7] [[Node: mul = Mul[T=DT_FLOAT , _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_Placeholder_0_0, Log)]]

由操作“mul”引起，定义在：文件“”，第 1 行，文件“C:\Users\Charlene\AppData\Local\Programs\Python\Python35\lib\idlelib\run.py”，第 130 行，在main ret = method(*args, **kwargs) 文件“C:\Users\Charlene\AppData\Local\Programs\Python\Python35\lib\idlelib\run.py”，第 357 行，运行代码 exec(code, self .locals) 文件“”，第 2 行，文件“C:\Users\Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\math_ops.py”，第 979 行，在 binary_op_wrapper 返回 func(x, y, name=name) 文件“C:\Users\Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\math_ops.py”，行1211，在 _mul_dispatch 返回 gen_math_ops.mul(x, y, name=name) 文件“C:\Users\Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\gen_math_ops.py”，第 5066 行，在 mul“Mul”中，x=x，y=y，名称=name）文件“C:\Users\Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py”，第 787 行，在 _apply_op_helper op_def=op_def）文件中“ C:\Users\Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\ops.py”，第 3392 行，在 create_op op_def=op_def) 文件“C:\Users\ Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\ops.py”，第 1718 行，在名称=名称）文件“C:\Users\Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py”，第 787 行，在 _apply_op_helper op_def=op_def）文件中“C:\Users\Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\ops.py”，第 3392 行，在 create_op op_def=op_def) 文件“C:\Users \Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\ops.py"，第 1718 行，在名称=名称）文件“C:\Users\Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py”，第 787 行，在 _apply_op_helper op_def=op_def）文件中“C:\Users\Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\ops.py”，第 3392 行，在 create_op op_def=op_def) 文件“C:\Users \Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\ops.py"，第 1718 行，在在 create_op op_def=op_def) 文件“C:\Users\Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\ops.py”中，第 1718 行在 create_op op_def=op_def) 文件“C:\Users\Charlene\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\ops.py”中，第 1718 行init self._traceback = self._graph._extract_stack() # pylint: disable=protected-access

InvalidArgumentError（参见上面的回溯）：不兼容的形状：[10,7] vs. [20,7] [[Node: mul = Mul[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0 /device:CPU:0"](_arg_Placeholder_0_0, 日志)]]

我在这里看到的主要错误是：

不兼容的形状：[10,7] 与 [20,7]

其中 10 是批量大小，7 是类数。

是什么导致错误？

标签： tensorflowdeep-learninglstmconvolutional-neural-network

Answer 1

似乎错误发生在这里：

loss = -tf.reduce_sum(Y * tf.log(y_))

你Y的 is (10, 7)，这是意料之中的，但y_由于某种原因是(20, 7)。

尝试追踪这条线之前的形状c2：

c2Reshape = tf.reshape(c2, [-1, 7, 200])

以及它之后的形状c2Reshape（或者只是暂时替换那条线，c2Reshape = tf.reshape(c2, [10, 7, 200])看看它是否失败），我怀疑这就是 20 的来源。