CNN 准确性不会在多个时期内发生变化

Question

我正在尝试创建一个 CNN，它可以区分有/没有糖尿病视网膜病变症状的眼睛的黑白照片。当我尝试运行我的模型时，准确性根本没有提高。我尝试使用不同的学习率，但没有奏效。由于这是我第一次制作 CNN，我想我可能在其他地方犯了错误。如果您在我的代码中发现问题，请告诉我，非常感谢您的帮助。

Train on 980 samples, validate on 327 samples
Epoch 1/5
980/980 [==============================] - 777s 792ms/step - loss: 8.1986 - accuracy: 0.4653 - val_loss: 8.8154 - val_accuracy: 0.4251
Epoch 2/5
980/980 [==============================] - 666s 679ms/step - loss: 8.1986 - accuracy: 0.4653 - val_loss: 8.8154 - val_accuracy: 0.4251
Epoch 3/5
980/980 [==============================] - 672s 686ms/step - loss: 8.1986 - accuracy: 0.4653 - val_loss: 8.8154 - val_accuracy: 0.4251

这是我的代码：

DATADIR = "C:\\Users.."
CATEGORIES = ["nosymptoms", "symptoms"]
training_data = []
IMG_SIZE = 512
for category in CATEGORIES:
    path = os.path.join(DATADIR, category) #brings us to folder with categories
    class_num = CATEGORIES.index(category)
    for img in os.listdir(path):
        img_array = cv2.imread(os.path.join(path,img), cv2.IMREAD_GRAYSCALE)
        new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE)) #img resized and becomes array
        training_data.append([new_array, class_num]) #classification is appended to image 

import random
random.shuffle(training_data)
for sample in training_data[:10]:
    print(sample[1])#0 is the image array, 1 is the label
X = [] #features set
y = [] #labels
X = np.array(X).reshape(-1, IMG_SIZE, IMG_SIZE, 1)#shape of features (-1 means any), img size, 1 (b/c it is a grayscale) 
#Save data
import pickle
pickle_out = open("X.pickle","wb")
pickle.dump(X, pickle_out)
pickle_out.close()

pickle_out = open("y.pickle","wb")
pickle.dump(y, pickle_out)
pickle_out.close()

X = pickle.load(open("X.pickle", "rb"))
y = pickle.load(open("y.pickle", "rb"))

X = X/255.0

model = Sequential()

model.add(Convolution2D(32, (3,3),input_shape=(X.shape[1:]),activation='relu'))
model.add(Convolution2D(32, (3,3),activation='relu'))
model.add(Convolution2D(32, (3,3),activation='relu'))

model.add(MaxPooling2D(pool_size=(2,2)))

model.add(Flatten())
model.add(Dense(16, activation='relu'))
model.add(Dense(12, activation='relu'))
model.add(Dense(1, activation='softmax'))

from keras.optimizers import SGD
opt = SGD(lr=0.01)
model.compile(loss = "binary_crossentropy", optimizer = opt, metrics=['accuracy'])
print(model.summary())

model.fit(X, y, batch_size = 16, epochs = 5, validation_split=.25)

Answer 1

因为你有 2 个类，所以将你的最后一层更改为 2 个神经元

model = Sequential() 
model.add(Convolution2D(32, (3,3),input_shape=(X.shape[1:]),activation='relu'))
model.add(Convolution2D(32, (3,3),activation='relu'))
model.add(Convolution2D(32, (3,3),activation='relu'))

model.add(MaxPooling2D(pool_size=(2,2)))

model.add(Flatten())
model.add(Dense(16, activation='relu'))
model.add(Dense(12, activation='relu'))
model.add(Dense(2, activation='softmax'))

from keras.optimizers import SGD
opt = SGD(lr=0.01)
model.compile(loss = "categorical_crossentropy", optimizer = opt, metrics=['accuracy'])
print(model.summary())

model.fit(X, y, batch_size = 16, epochs = 5, validation_split=.25)