如何在 2D 向量上使用 reshape() 函数

Question

我已经重新塑造了一个特征向量，但仍然出现此错误：

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.

我在预测之前使用了reshape

features = features.reshape(1, -1)

但一点运气都没有。

这是我的代码

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
    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)

我不知道是我错误地使用了 reshape() 还是遗漏了一些东西。

ValueError：预期的 2D 数组，得到 1D 数组：array=[]。 如果您的数据具有单个特征，则使用 array.reshape(-1, 1) 重塑您的数据，如果它包含单个样本，则使用 array.reshape(1, -1)。

Answer 1

考虑以下几点：

• 由于train_features 是clf_svm.fit(train_features, train_labels) 行中的[ ]（空列表），因此出现上述错误。它应该至少包含1 数据。这是因为train_path 指向仅包含图像文件的文件夹，但上面的代码假设train_path 指向至少具有1 子文件夹（无文件）的文件夹。

  train 
     - class1_folder[class11.jpg, class12.jpg, ...]
     - class2_folder[class21.jpg, class22.jpg, ...]
     - and so on ...
  

  在这里，您的训练数据的类名将是[class1, class2, ...]

• 把train_features.append(features.reshape(1, -1))[0]改成train_features.append(features.reshape(1, -1)[0])

• clf_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)。您也可以将其替换为 prediction[0]。

试试下面的代码：

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()