Question

我正在建立一个卷积网络来预测3类图像，猫，狗和人。我训练并训练了它，但是随后当我通过猫的图像进行预测时，总是给出错误的输出。我试过其他猫的照片，但结果没有改变。对于人和狗来说，没有问题，只与猫一样。

     cnn = Sequential()

    #------------------- Convolução e Pooling
    cnn.add(Conv2D(32, (3, 3), input_shape = (64, 64, 3), activation = 'relu'))
    cnn.add(Dropout(0.5))
    cnn.add(MaxPooling2D(pool_size = (2, 2)))

    cnn.add(Conv2D(32, (3, 3), activation = 'relu'))
    cnn.add(Dropout(0.5))
    cnn.add(MaxPooling2D(pool_size = (2, 2)))

    cnn.add(Conv2D(64, (3, 3), activation = 'relu'))
    cnn.add(MaxPooling2D(pool_size = (2, 2)))

    cnn.add(Conv2D(64, (3, 3), activation = 'relu'))
    cnn.add(Dropout(0.5))
    cnn.add(MaxPooling2D(pool_size = (2, 2)))

    #Full connection
    cnn.add(Flatten())
    cnn.add(Dense(units = 128, activation = 'relu'))
    cnn.add(Dense(units = 4, activation = 'softmax'))

    # Compiling the CNN
    cnn.compile(optimizer = OPTIMIZER, loss = 'categorical_crossentropy', metrics = ['accuracy'])

    filepath="LPT-{epoch:02d}-{loss:.4f}.h5"
    checkpoint = ModelCheckpoint(filepath, monitor='loss', verbose=1, save_best_only=True, mode='min')
    callbacks_list = [checkpoint]

12000张火车图像-3000张测试图像

train_datagen = ImageDataGenerator(rescale = 1./255,
                                   shear_range = 0.2,
                                   zoom_range = 0.2,
                                   horizontal_flip = True)

test_datagen = ImageDataGenerator(rescale = 1./255)

training_set = train_datagen.flow_from_directory('data/train',
                                                 target_size = tgt_size,
                                                 batch_size = batch_size,
                                                 class_mode = 'categorical')

test_set = test_datagen.flow_from_directory('data/test',
                                            target_size = tgt_size,
                                            batch_size = batch_size,
                                            class_mode = 'categorical')

cnn.fit_generator(training_set,
                  #steps_per_epoch = 12000,  
                  steps_per_epoch = nb_train_samples // batch_size,                                                   
                  epochs = EPOCHS,
                  verbose = VERBOSE,
                  validation_data = test_set,
                  validation_steps = nb_validation_samples // batch_size,
                  callbacks = callbacks_list)

我最好的训练结果：

loss: 0.6410 - acc: 0.7289 - val_loss: 0.6308 - val_acc: 0.7293

类索引：

{'.ipynb_checkpoints': 0, 'cats': 1, 'dogs':2, 'person':3}

（我无法删除该ipynb文件夹）

预测：

pred1 = 'single_prediction/ct.jpg'
pred2 = 'single_prediction/ps.jpg'
pred3 = 'data/single_prediction/dg.jpg'

test_img = image.load_img(pred1, target_size = tgt_size)
test_img = image.img_to_array(test_img)
test_img = np.expand_dims(test_img, axis = 0)
pred = new_model.predict(test_img)
print(pred)

if pred[0][1] == 1:
        print('It is a cat!')
elif pred[0][2] == 1:
    print('It is a dog!')
elif pred[0][3] == 1:
    print('It is a Person!')

以及猫图像的输出：

[[0.000000e+00 0.000000e+00 8.265931e-34 1.000000e+00]]

我已经尝试过：更改层数（添加和删除），增加历元，减少批处理...我也尝试使用np.argmax（）。有人可以在这里给我点灯吗？

更新：我使用shutil.rmtree（）命令删除了jupyter笔记本的隐藏文件夹，并对其进行了大约40个时期的训练，直到停止改进。最后，我对预测图像进行了重新缩放并正确处理。

test_img = image.img_to_array(test_img)/255

感谢所有帮助！

Answer 1

问题出在ipynb checkpoints文件夹。这是一个隐藏的文件夹。您需要先删除它。然后将您的输出密集层更改为3个单位（类）。改变这个

cnn.add(Dense(units = 4, activation = 'softmax'))

到

cnn.add(Dense(units = 3, activation = 'softmax'))

CNN-具有多分类的错误预测

1 个答案: