Python 如何在二维向量上使用整形（）函数

我重新塑造了一个特征向量，但仍然出现以下错误：

ValueError: Expected 2D array, got 1D array instead: array=[].
Reshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.

我在预测之前使用过重塑，比如

features = features.reshape(1, -1)

但是一点运气都没有

这是我的密码

import cv2
import numpy as np
import os
import glob
import mahotas as mt
from sklearn.svm import LinearSVC

# function to extract haralick textures from an image
def extract_features(image):
    # calculate haralick texture features for 4 types of adjacency
    textures = mt.features.haralick(image)

    # take the mean of it and return it
    ht_mean = textures.mean(axis = 0).reshape(1, -1)
    return ht_mean

# load the training dataset
train_path  = "C:/dataset/train"
train_names = os.listdir(train_path)

# empty list to hold feature vectors and train labels
train_features = []
train_labels   = []

# loop over the training dataset
print ("[STATUS] Started extracting haralick textures..")
for train_name in train_names:
    cur_path = train_path + "/" + train_name
    cur_label = train_name
    i = 1

    for file in glob.glob(cur_path + "/*.jpg"):
        print ("Processing Image - {} in {}".format(i, cur_label))
        # read the training image
        image = cv2.imread(file)

        # convert the image to grayscale
        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

        # extract haralick texture from the image
        features = extract_features(gray)

        # append the feature vector and label
        train_features.append(features.reshape(1, -1))[0]
        train_labels.append(cur_label)

        # show loop update
        i += 1

# have a look at the size of our feature vector and labels
print ("Training features: {}".format(np.array(train_features).shape))
print ("Training labels: {}".format(np.array(train_labels).shape))

# create the classifier
print ("[STATUS] Creating the classifier..")
clf_svm = LinearSVC(random_state = 9)

# fit the training data and labels
print ("[STATUS] Fitting data/label to model..")
clf_svm.fit(train_features, train_labels)

# loop over the test images
test_path = "C:/dataset/test"
for file in glob.glob(test_path + "/*.jpg"): 
    # read the input image
    image = cv2.imread(file)

    # convert to grayscale
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    # extract haralick texture from the image
    features = extract_features(gray)

    # evaluate the model and predict label
    prediction = clf_svm.predict(features)

    # show the label
    cv2.putText(image, prediction, (20,30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0,255,255), 3)
    print ("Prediction - {}".format(prediction))

    # display the output image
    cv2.imshow("Test_Image", image)
    cv2.waitKey(0)

我不知道我是否错误地使用了整形（）或缺少了什么

ValueError:应为2D数组，而应为1D数组：数组=[]。

---

使用数组重塑数据。如果数据具有单个特征或数组，则重塑（-1，1）。如果数据包含单个样本，则重塑（1，-1）。

请考虑以下几点：

• 出现上述错误是因为

  train\u features

  在

  clf\u svm.fit（train\u features，train\u label）

  行中为[]（空列表）。它应至少包含

  1

  数据。这是因为

  train\u path

  指向一个仅包含图像文件的文件夹，但上述代码假设

  train\u path

  指向一个至少包含

  1

  子文件夹（无文件）的文件夹
  在这里，培训数据的类名将是

  [class1，class2，…]

• 正确的行

  train\u features.append（features.reformate（1，-1））[0]

  到

  train\u features.append（features.reformate（1，-1）[0]）

• clf\u svm.predict（features）

  的输出是一个numpy数组。因此，在

  cv2.putText

  函数中将

  prediction

  替换为

  str（prediction）

  。您还可以将其替换为

  预测[0]

请尝试以下代码：

import cv2
import numpy as np
import os
import glob
import mahotas as mt
from sklearn.svm import LinearSVC

# function to extract haralick textures from an image
def extract_features(image):
    # calculate haralick texture features for 4 types of adjacency
    textures = mt.features.haralick(image)

    # take the mean of it and return it
    ht_mean = textures.mean(axis = 0).reshape(1, -1)
    return ht_mean

# load the training dataset
train_path  = "C:\\dataset\\train"
train_names = os.listdir(train_path)

# empty list to hold feature vectors and train labels
train_features = []
train_labels   = []

# loop over the training dataset
print ("[STATUS] Started extracting haralick textures..")
for train_name in train_names:
    cur_path = train_path + "\\" + train_name
    print(cur_path)
    cur_label = train_name
    i = 1

    for file in glob.glob(cur_path + "\*.jpg"):
        print ("Processing Image - {} in {}".format(i, cur_label))
        # read the training image
        #print(file)
        image = cv2.imread(file)
        #print(image)

        # convert the image to grayscale
        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

        # extract haralick texture from the image
        features = extract_features(gray)
        #print(features.reshape(1, -1))
        # append the feature vector and label
        train_features.append(features.reshape(1, -1)[0])
        train_labels.append(cur_label)

        # show loop update
        i += 1

# have a look at the size of our feature vector and labels
print ("Training features: {}".format(np.array(train_features).shape))
print ("Training labels: {}".format(np.array(train_labels).shape))

# create the classifier
print ("[STATUS] Creating the classifier..")
clf_svm = LinearSVC(random_state = 9)

# fit the training data and labels
print ("[STATUS] Fitting data/label to model..")
print(train_features)
clf_svm.fit(train_features, train_labels)

# loop over the test images
test_path = "C:\\dataset\\test"
for file in glob.glob(test_path + "\*.jpg"): 
    # read the input image
    image = cv2.imread(file)

    # convert to grayscale
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    # extract haralick texture from the image
    features = extract_features(gray)

    # evaluate the model and predict label
    prediction = clf_svm.predict(features)

    # show the label
    cv2.putText(image, str(prediction), (20,30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0,255,255), 3)
    print ("Prediction - {}".format(prediction))

    # display the output image
    cv2.imshow("Test_Image", image)
    cv2.waitKey(0)
cv2.destroyAllWindows()

---

谢谢你的回答，阿努巴夫。我试过你的回答，但现在我得到了这个警告<代码>收敛警告：Liblinear无法收敛，请增加迭代次数。环顾四周，我发现我必须增加迭代次数。你认为呢？为了补充上面的评论，我在

LinearSVC

中使用了

dual=False

，以避免警告，但该过程仍然中止。但是，请告诉我一件事，你的路径是什么：

C:\\dataset\\train

。它需要包含包含.jpg文件的类文件夹。请在

LinearSVC

model中尝试

max\u iter=10000

。如果这不起作用，请尝试在0-1之间缩放数据以处理

收敛警告：Liblinear无法收敛，请增加迭代次数

。我修复了您告诉我的测试集中的路径。没有意识到没有必要在其中包含子文件夹。非常感谢你。

import cv2
import numpy as np
import os
import glob
import mahotas as mt
from sklearn.svm import LinearSVC

# function to extract haralick textures from an image
def extract_features(image):
    # calculate haralick texture features for 4 types of adjacency
    textures = mt.features.haralick(image)

    # take the mean of it and return it
    ht_mean = textures.mean(axis = 0).reshape(1, -1)
    return ht_mean

# load the training dataset
train_path  = "C:\\dataset\\train"
train_names = os.listdir(train_path)

# empty list to hold feature vectors and train labels
train_features = []
train_labels   = []

# loop over the training dataset
print ("[STATUS] Started extracting haralick textures..")
for train_name in train_names:
    cur_path = train_path + "\\" + train_name
    print(cur_path)
    cur_label = train_name
    i = 1

    for file in glob.glob(cur_path + "\*.jpg"):
        print ("Processing Image - {} in {}".format(i, cur_label))
        # read the training image
        #print(file)
        image = cv2.imread(file)
        #print(image)

        # convert the image to grayscale
        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

        # extract haralick texture from the image
        features = extract_features(gray)
        #print(features.reshape(1, -1))
        # append the feature vector and label
        train_features.append(features.reshape(1, -1)[0])
        train_labels.append(cur_label)

        # show loop update
        i += 1

# have a look at the size of our feature vector and labels
print ("Training features: {}".format(np.array(train_features).shape))
print ("Training labels: {}".format(np.array(train_labels).shape))

# create the classifier
print ("[STATUS] Creating the classifier..")
clf_svm = LinearSVC(random_state = 9)

# fit the training data and labels
print ("[STATUS] Fitting data/label to model..")
print(train_features)
clf_svm.fit(train_features, train_labels)

# loop over the test images
test_path = "C:\\dataset\\test"
for file in glob.glob(test_path + "\*.jpg"): 
    # read the input image
    image = cv2.imread(file)

    # convert to grayscale
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    # extract haralick texture from the image
    features = extract_features(gray)

    # evaluate the model and predict label
    prediction = clf_svm.predict(features)

    # show the label
    cv2.putText(image, str(prediction), (20,30), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0,255,255), 3)
    print ("Prediction - {}".format(prediction))

    # display the output image
    cv2.imshow("Test_Image", image)
    cv2.waitKey(0)
cv2.destroyAllWindows()