混淆矩阵值错误：找到样本数量不一致的输入变量：[3, 360]

Posted 2023-03-12

【中文标题】混淆矩阵值错误：找到样本数量不一致的输入变量：[3, 360]

【英文标题】：Confusion Matrix ValueError: Found input variables with inconsistent numbers of samples: [3, 360]

【发布时间】：2020-12-27 01:17:16

【问题描述】：

我正在尝试训练一个数据集，并在训练完数据集后输出一个混淆矩阵。

这里是代码

import tensorflow as tf

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Conv2D, Flatten, Dropout, MaxPooling2D
from tensorflow.keras.preprocessing.image import ImageDataGenerator 

from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras import Input

from tensorflow.keras.layers import Dropout
from tensorflow.keras.layers import Softmax
from tensorflow.keras.layers import GlobalAveragePooling2D
from tensorflow.keras.layers import Convolution2D

import os
import numpy as np
import matplotlib.pyplot as plt

import scipy as sp 
from scipy import signal
from scipy.signal import chirp
import numpy.fft
from numpy.fft import fft as rf
import random
import pandas as pd
import sklearn.model_selection as model_selection
import matplotlib.pyplot as plt
import tensorflow as tf

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Conv2D, Flatten, Dropout, MaxPooling2D
from tensorflow.keras.preprocessing.image import ImageDataGenerator 

from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras import Input

from tensorflow.keras.layers import Dropout
from tensorflow.keras.layers import Softmax
from tensorflow.keras.layers import GlobalAveragePooling2D
from tensorflow.keras.layers import Convolution2D

import os
import numpy as np
import matplotlib.pyplot as plt

import scipy as sp 
from scipy import signal
from scipy.signal import chirp
import numpy.fft
from numpy.fft import fft as rf
import random
import pandas as pd
import sklearn.model_selection as model_selection
import matplotlib.pyplot as plt

from sklearn.datasets import make_blobs
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import brier_score_loss
from sklearn.calibration import CalibratedClassifierCV
from sklearn.model_selection import train_test_split

from sklearn.datasets import make_blobs
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import brier_score_loss
from sklearn.calibration import CalibratedClassifierCV
from sklearn.model_selection import train_test_split

from PIL import Image
import imageio as io 
import glob
from matplotlib import image

  
import h5py
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, Activation, concatenate
from tensorflow.keras.layers import Flatten, Dropout
from tensorflow.keras.layers import Convolution2D, MaxPooling2D
from tensorflow.keras.layers import AveragePooling2D

from tensorflow.keras.layers import Input, Conv2D, Concatenate, \
     MaxPool2D, GlobalAvgPool2D, Activation

def squeezenet(input_shape, n_classes):
  
  def fire(x, fs, fe):
    s = Conv2D(fs, 1, activation='relu')(x)
    e1 = Conv2D(fe, 1, activation='relu')(s)
    e3 = Conv2D(fe, 3, padding='same', activation='relu')(s)
    output = Concatenate()([e1, e3])
    return output
  
  
  input = Input(input_shape)
  
  x = Conv2D(96, 7, strides=2, padding='same', activation='relu')(input)
  x = MaxPool2D(3, strides=2, padding='same')(x)
  
  x = fire(x, 16, 64)
  x = fire(x, 16, 64)
  x = fire(x, 32, 128)
  x = MaxPool2D(3, strides=2, padding='same')(x)
  
  x = fire(x, 32, 128)
  x = fire(x, 48, 192)
  x = fire(x, 48, 192)
  x = fire(x, 64, 256)
  x = fire(x, 64, 256)
  x = MaxPool2D(3, strides=2, padding='same')(x)
    
  x = Dropout(0.6)(x)
    
  x = Conv2D(n_classes, 1)(x)
  x = GlobalAvgPool2D()(x)
  x = Flatten()(x)
  
  output = Activation('softmax')(x)
  
  model = Model(input, output)
  return model

  import pathlib
import PIL

test_datagen = ImageDataGenerator(rescale=1./255)


data_dir = os.path.join(r"location/directory of the file", "file")

data_dir = pathlib.Path(data_dir)

image_count = len(list(data_dir.glob('*/*.png')))
print(image_count)

rect = list(data_dir.glob('Rect/*'))
PIL.Image.open(str(rect[1]))


batch_size = 32
img_height = 227
img_width = 227

train_ds = tf.keras.preprocessing.image_dataset_from_directory(
  data_dir,
  validation_split=0.1,
  subset="training",
  seed=123,
  image_size=(img_height, img_width),
  batch_size=batch_size)

val_ds = tf.keras.preprocessing.image_dataset_from_directory(
  data_dir,
  validation_split=0.1,
  subset="validation",
  seed=123,
  image_size=(img_height, img_width),
  batch_size=batch_size)

class_names = train_ds.class_names
print(range(len(class_names)))

AUTOTUNE = tf.data.experimental.AUTOTUNE

train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)

normalization_layer = layers.experimental.preprocessing.Rescaling(1./255)

normalized_ds = train_ds.map(lambda x, y: (normalization_layer(x), y))
image_batch, labels_batch = next(iter(normalized_ds))
first_image = image_batch[0]
# Notice the pixels values are now in `[0,1]`.
print(np.min(first_image), np.max(first_image)) 

from keras.optimizers import SGD
from keras.callbacks import EarlyStopping, ModelCheckpoint
from keras.preprocessing.image import ImageDataGenerator


model = squeezenet((227,227,3),2)

sgd = SGD(lr=0.001, decay=0.0002, momentum=0.9, nesterov=True)
model.compile(
optimizer=sgd, loss='binary_crossentropy', metrics=['accuracy'])

print(model.summary())

acc = history.history['accuracy']
val_acc = history.history['val_accuracy']

loss=history.history['loss']
val_loss=history.history['val_loss']

epochs_range = epoch #range(epochs)

plt.figure(figsize=(8, 8))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']

loss=history.history['loss']
val_loss=history.history['val_loss']

epochs_range = epoch #range(epochs)

plt.figure(figsize=(8, 8))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

#supply a imafe to classifer to get an image out 
#calculate the confusion matrix manualy 

from sklearn.metrics import classification_report, confusion_matrix


Y_pred = model.predict_generator(val_ds, 720 // 32+1)
y_pred = np.argmax(Y_pred, axis=1)
print(y_pred.shape)
print('Confusion Matrix')
print(confusion_matrix(class_names, y_pred))
print('Classification Report')
target_names = ['Cats', 'Dogs', 'Horse']
print(classification_report(class_names, y_pred, target_names=target_names))

这是我遇到的错误。

ValueError                                Traceback (most recent call last)
<ipython-input-9-5188ce05905a> in <module>
      9 print(y_pred.shape)
     10 print('Confusion Matrix')
---> 11 print(confusion_matrix(class_names, y_pred))
     12 print('Classification Report')
     13 target_names = ['Cats', 'Dogs', 'Horse']

in confusion_matrix(y_true, y_pred, labels, sample_weight)
    251 
    252     """
--> 253     y_type, y_true, y_pred = _check_targets(y_true, y_pred)
    254     if y_type not in ("binary", "multiclass"):
    255         raise ValueError("%s is not supported" % y_type)

in _check_targets(y_true, y_pred)
     69     y_pred : array or indicator matrix
     70     """
---> 71     check_consistent_length(y_true, y_pred)
     72     type_true = type_of_target(y_true)
     73     type_pred = type_of_target(y_pred)

in check_consistent_length(*arrays)
    203     if len(uniques) > 1:
    204         raise ValueError("Found input variables with inconsistent numbers of"
--> 205                          " samples: %r" % [int(l) for l in lengths])
    206 
    207 

ValueError: Found input variables with inconsistent numbers of samples: [3, 360]

【问题讨论】：

请删除（大量...）重复导入，以及与当前问题无关的内容（情节等）；看看为什么a wall of code isn't helpful

【参考方案1】：

confusion_matrix 方法中的参数应该是 y_true 和 y_pred，因为你可以找到 in the doc。

您的第一个参数y_true (=class_names) 的大小似乎是 3，而您的第二个参数 y_pred 的大小似乎是 360。但是两者的大小应该相同，因为 y_pred 是您分类的估计结果y_true 是它的基本事实。

这是使用 3 个类的 sklearn 相关示例：[0, 1, 2]

from sklearn.metrics import confusion_matrix
y_true = [2, 0, 2, 2, 0, 1]
y_pred = [0, 0, 2, 2, 0, 2]
confusion_matrix(y_true, y_pred)

编辑

y_true 是如何构造的？

通常y_true 包含与您的每个输入相对应的每个标签。您似乎为分类器提供了 360 个输入，因此您应该为每个输入提供一个关联标签，即您的 class_names 之一。这个包含您输入的真实标签的完整向量是y_true。

【讨论】：

在这种情况下，什么是正确的

我已经更新了问题：您的y_true 应该与您的y_pred 具有相同的大小。 y_true 包含预期结果的真实值。希望对你有帮助

我想另一个问题是因为我的验证大小是 360。这就是正在训练的内容，所以我将如何创建 Y True 以使其与我的混淆矩阵一起使用

我刚刚更新了问题以详细说明如何构造y_true。希望对你有帮助