我想用圖像測試我的圖像分類模型。但我得到一些錯誤： --> path = 'E:/My Work Elements/Thesis Related/Trash Classification/Trash New Code/test/cardboard/cardboard42.jpg' test_single_image(path) Traceback (most recent call last): File "<ipython-input-15-4a6021aada0c>", line 2, in <module> test_single_image(path) File "<ipython-input-14-1654f8f7a46b>", line 3, in test_single_image images = read_image(path) NameError: name 'read_image' is not defined我使用這段代碼：def test_single_image(path): Garbage = ['cardboard','Glass','Metal','paper','plastic','Trash'] images = read_image(path) time.sleep(.5) bt_prediction = vgg16.predict(images) preds = model.predict_proba(bt_prediction) for idx, Garbage, x in zip(range(0,6), Garbage , preds[0]): print("ID: {}, Label: {} {}%".format(idx, Garbage, round(x*100,2) )) print('Final Decision:') time.sleep(.5) for x in range(3): print('.'*(x+1)) time.sleep(.2) class_predicted = model.predict_classes(bt_prediction) class_dictionary = generator_top.class_indices print(class_dictionary) inv_map = {v: k for k, v in class_dictionary.items()} print("Class: {}, prediction Result: {}".format(class_predicted[0], inv_map[class_predicted[0]])) return load_img(path, target_size=(224,224))path = 'E:/My Work Elements/Thesis Related/Trash Classification/Trash New Code/test/cardboard/cardboard42.jpg'test_single_image(path)如何修復代碼？
2 回答
蕪湖不蕪
TA貢獻1796條經驗 獲得超7個贊
您可以使用 keras VGG16 API 輕松獲取 VGG16 模型
from keras.applications.vgg16 import VGG16
from keras.preprocessing import image
from keras.applications.vgg16 import preprocess_input
import numpy as np
model = VGG16(weights='imagenet', include_top=False)
img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
features = model.predict(x)
你read_image方法改變load_image方法。keras API 將調整圖像大小以滿足 vgg16 模型請求。
慕少森
TA貢獻2019條經驗 獲得超9個贊
如果您使用 opencv 讀取圖像，它應該是 cv2.imread()。就我使用 vgg16 而言，應該有一個 read_image 函數之前定義，它接收任何形狀的圖像，將其調整為標準形狀（224 * 224 * 3）并進行所需的任何其他類型的預處理。
如果您使用的是 keras 預處理，它有一個預定義的 load_img 函數，可以為您進行預處理。
例子 ：
from keras.preprocessing.image import load_img
load_image(path,target_size= (224*224*3))
我的樣本加載功能
from keras.preprocessing import image
from keras.applications.imagenet_utils import decode_predictions, preprocess_input
def load_image(path):
img = image.load_img(path,target_size=model.input_shape[1:3])
x = image.img_to_array(img)
x = np.expand_dims(x,axis=0)
x = preprocess_input(x)
return img,x
添加回答
舉報
0/150
提交
取消