获得固定精度：使用 Google Colab 在 Keras 模型中为 0.5000，有时为 0.0000e+00

Question

我正在使用 Google Colab 上的 Keras 训练一个 CNN 模型进行二进制图像分类，问题是当我使用 Sigmoid 函数时，我的准确度固定在 0.5000，当我将指标更改为“acc”时，我得到 0.000e+00 作为准确性。此外，当我将激活函数更改为“Softmax”时，我的模型开始学习。

Ps：我正在使用 google colab，其中 Tensorflow 版本为 2.5.0

我的代码：

def define_model(input_shape, num_classes):
    model=ResNet50(include_top = False, weights = 'imagenet', input_shape = input_shape)
    x = model.output
    x = GlobalAveragePooling2D()(x)
    preds = Dense(num_classes,activation='sigmoid')(x) 
    model = Model(inputs=model.input,outputs=preds)
    return model

def train(epochs):   

    train_generator = ImageDataGenerator(rescale=1.0/255.0,vertical_flip=True, horizontal_flip=True)                                                                                                                           
    test_generator = ImageDataGenerator(rescale=1.0/255.0)

    train_generator = train_generator.flow_from_directory(
        'trainset/',
        target_size=(image_size, image_size),
        batch_size=BATCH_SIZE_TRAINING,
        seed = 7)

    validation_generator = test_generator.flow_from_directory(
        'testset/',
        target_size=(image_size, image_size),
        batch_size=BATCH_SIZE_VALIDATION,
        seed = 7)

    input_shape = (CHANNELS, image_size, image_size) if K.image_data_format() == 'channels_first' \
            else (image_size, image_size, CHANNELS) 
            
    model = define_model(input_shape, NUM_CLASSES)

    opt = optimizers.Adam(learning_rate=1e-6, beta_1=0.9, beta_2=0.99, amsgrad=False)

    model.summary()
    model.compile(loss='binary_crossentropy',
                  optimizer=opt,
                  metrics=['acc'])
               
    filepath=path+"weights-improvement-{epoch:02d}-vacc:{val_accuracy:.2f}-tacc:{accuracy:.2f}.hdf5"
    '''cb_early_stopper = EarlyStopping(monitor = 'val_accuracy', mode='min', verbose=1, patience = EARLY_STOP_PATIENCE)
    cb_checkpointer = ModelCheckpoint(filepath = filepath, monitor = 'val_accuracy', save_best_only = True, mode = 'auto')
    reduce_lr = ReduceLROnPlateau(monitor='val_accuracy', factor=0.25, patience=5, min_lr=1e-7)'''
    fit_history = model.fit(train_generator,
            epochs = NUM_EPOCHS,
            validation_data=validation_generator,
            verbose=1,
            class_weight=class_weights)
#            callbacks = [cb_checkpointer, cb_early_stopper, reduce_lr],
            
    return model, fit_history
        
def main():
    
    start_time = time()
    model, fit_history = train(epochs=NUM_EPOCHS)    
    end_time = time()
    seconds_elapsed = end_time - start_time
    print('token time: ', seconds_elapsed)
    hours, rest = divmod(seconds_elapsed, 3600)
    minutes, seconds = divmod(rest, 60)
    
if __name__ == "__main__":
    main()