希望大家度过美好的一天。我一直在研究一种类似FaceID的CNN类型模型，我的数据只有我的照片，模型没有错误，但在预测时总是给出相同的结果（对于每张脸都显示100%，即使不是我），我认为可能是Y值的问题，但我不确定。我想要的结果是区分是我还是其他人。以下是我的代码
# Face ID project, using CNN tensorflowfrom tensorflow.keras.preprocessing.image import img_to_arrayfrom tensorflow.keras.optimizers import Adam from tensorflow.keras.models import Sequentialfrom tensorflow.keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D, BatchNormalization, Activationfrom tensorflow.keras import backend as Kimport numpy as npimport cv2 import glob# Preparing the data and parametersepochs = 100lr = 1e-3batch_size = 64 img_dims = (96,96,3)data = []labels = []image_files = glob.glob("C:/Users/berna/Desktop/Programming/AI_ML_DL/Projects/FaceID/Data/*")for img in image_files: image = cv2.imread(img) image = cv2.resize(image, (img_dims[0], img_dims[1])) image = img_to_array(image) data.append(image) if img == img: label = 1 else: label = 0 labels.append([label]) # Preproccesing the data (convert arrays)data = np.array(data, dtype="float32") / 255.0labels = np.array(labels)X = data y = labelsdef build(width, height, depth, classes): model = Sequential() inputShape = height, width, depth chanDim = -1 if K.image_data_format() == "channels_first": inputShape = depth, height, width chanDim = 1 # Creating the model model.add(Conv2D(32, (3,3), padding="same", input_shape=inputShape)) model.add(Activation("relu")) model.add(BatchNormalization(axis=chanDim)) model.add(MaxPooling2D(pool_size=(3,3))) model.add(Dropout(0.25)) model.add(Conv2D(64, (3,3), padding="same")) model.add(Activation("relu")) model.add(BatchNormalization(axis=chanDim)) model.add(Conv2D(64, (3,3), padding="same")) model.add(Activation("relu")) model.add(BatchNormalization(axis=chanDim)) model.add(MaxPooling2D(pool_size=(2,2))) model.add(Dropout(0.25)) model.add(Conv2D(128, (3,3), padding="same")) model.add(Activation("relu")) model.add(BatchNormalization(axis=chanDim)) model.add(Conv2D(128, (3,3), padding="same")) model.add(Activation("relu")) model.add(BatchNormalization(axis=chanDim)) model.add(MaxPooling2D(pool_size=(2,2))) model.add(Dropout(0.25)) model.add(Flatten()) model.add(Dense(1024)) model.add(Activation("relu")) model.add(BatchNormalization()) model.add(Dropout(0.5)) model.add(Dense(1)) model.add(Activation("sigmoid")) return model# Build the model call model = build(width=img_dims[0], height=img_dims[1], depth=img_dims[2], classes=1)# compile the modelopt = Adam(lr=lr, decay=lr/epochs)model.compile(loss="binary_crossentropy", optimizer=opt, metrics=['accuracy'])# fitting the modelH = model.fit(X, y, batch_size=batch_size, epochs=epochs, verbose=1)model.save('faceid.model')有什么想法吗？
编辑我修改了我的代码和数据集，现在其他人的标记为1，我自己的标记为0，但在预测时仍然只预测一种结果，以下是我的代码
# Face ID project, using CNN tensorflowfrom tensorflow.keras.preprocessing.image import img_to_arrayfrom tensorflow.keras.optimizers import Adam from tensorflow.keras.models import Sequentialfrom tensorflow.keras.utils import to_categoricalfrom tensorflow.keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D, BatchNormalization, Activationfrom tensorflow.keras import backend as Kimport numpy as npimport randomimport cv2 import globimport os# Preparing the data and parametersepochs = 100lr = 1e-3batch_size = 64 img_dims = (96,96,3)data = []labels = []image_files = [f for f in glob.glob("C:/Users/berna/Desktop/Programming/AI_ML_DL/Projects/FaceID/Data"+"/**/*", recursive=True) if not os.path.isdir(f)]random.shuffle(image_files)for img in image_files: image = cv2.imread(img) image = cv2.resize(image, (img_dims[0], img_dims[1])) image = img_to_array(image) data.append(image) label = img.split(os.path.sep)[-2] if label == "Other": label = 1 else: label = 0 labels.append([label]) # Preproccesing the data (convert arrays)data = np.array(data, dtype="float32") / 255.0labels = np.array(labels)X = data y = to_categorical(labels, num_classes=2)def build(width, height, depth, classes): model = Sequential() inputShape = height, width, depth chanDim = -1 if K.image_data_format() == "channels_first": inputShape = depth, height, width chanDim = 1 # Creating the model model.add(Conv2D(32, (3,3), padding="same", input_shape=inputShape)) model.add(Activation("relu")) model.add(BatchNormalization(axis=chanDim)) model.add(MaxPooling2D(pool_size=(3,3))) model.add(Dropout(0.25)) model.add(Conv2D(64, (3,3), padding="same")) model.add(Activation("relu")) model.add(BatchNormalization(axis=chanDim)) model.add(Conv2D(64, (3,3), padding="same")) model.add(Activation("relu")) model.add(BatchNormalization(axis=chanDim)) model.add(MaxPooling2D(pool_size=(2,2))) model.add(Dropout(0.25)) model.add(Conv2D(128, (3,3), padding="same")) model.add(Activation("relu")) model.add(BatchNormalization(axis=chanDim)) model.add(Conv2D(128, (3,3), padding="same")) model.add(Activation("relu")) model.add(BatchNormalization(axis=chanDim)) model.add(MaxPooling2D(pool_size=(2,2))) model.add(Dropout(0.25)) model.add(Flatten()) model.add(Dense(1024)) model.add(Activation("relu")) model.add(BatchNormalization()) model.add(Dropout(0.5)) model.add(Dense(classes)) model.add(Activation("sigmoid")) return model# Build the model call model = build(width=img_dims[0], height=img_dims[1], depth=img_dims[2], classes=2)# compile the modelopt = Adam(lr=lr, decay=lr/epochs)model.compile(loss="binary_crossentropy", optimizer=opt, metrics=['accuracy'])# fitting the modelH = model.fit(X, y, batch_size=batch_size, epochs=epochs, verbose=1)model.save('faceid.model')回答：
答案就在你的问题中。你说你的数据只有你的照片。这意味着你用相同标签y = 1的照片训练了模型。所以模型总是预测y = 1是合乎逻辑的。如果你想让模型区分你的照片和其他人的照片，你必须使用你的照片和其他人照片来训练模型，并设置y = 1为你的照片，y = 0为其他人的照片。
注意：在你的代码中，这个if条件总是返回true：
if img == img: label = 1因为img等于它自己，所以标签总是等于1。
