如何在新图像上使用.predict_generator()-Keras [英] How to use .predict_generator() on new Images - Keras

问题描述

我已经使用ImageDataGenerator和flow_from_directory进行培训和验证.

I've used ImageDataGenerator and flow_from_directory for training and validation.

这些是我的目录:

train_dir = Path('D:/Datasets/Trell/images/new_images/training')
test_dir = Path('D:/Datasets/Trell/images/new_images/validation')
pred_dir = Path('D:/Datasets/Trell/images/new_images/testing')

ImageGenerator代码:

ImageGenerator Code:

img_width, img_height = 28, 28
batch_size=32
train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True)

test_datagen = ImageDataGenerator(rescale=1. / 255)

train_generator = train_datagen.flow_from_directory(
    train_dir,
    target_size=(img_height, img_width),
    batch_size=batch_size,
    class_mode='categorical')

validation_generator = test_datagen.flow_from_directory(
    test_dir,
    target_size=(img_height, img_width),
    batch_size=batch_size,
    class_mode='categorical')

找到了1852个属于4类的图像

Found 1852 images belonging to 4 classes

找到了115个属于4类的图像

Found 115 images belonging to 4 classes

这是我的模型训练代码:

This is my model training code:

history = cnn.fit_generator(
        train_generator,
        steps_per_epoch=1852 // batch_size,
        epochs=20,
        validation_data=validation_generator,
        validation_steps=115 // batch_size)

现在，我要在测试文件夹中有一些新图像(所有图像仅在同一文件夹内).但是当我使用.predict_generator时，我得到:

Now I have some new images in a test folder (all images are inside the same folder only), on which I want to predict. But when I use .predict_generator I get:

找到0个属于0类的图像

Found 0 images belonging to 0 class

所以我尝试了以下解决方案:

So I tried these solutions:

1) Keras:如何将predict_generator与ImageDataGenerator一起使用?无法解决，因为它仅尝试验证集.

1) Keras: How to use predict_generator with ImageDataGenerator? This didn't work out, because its trying on validation set only.

2)如何使用model.predict预测新图像? module image not found

3)如何使用predict_generator对Keras中的流式测试数据进行预测?这也没有奏效.

我的火车数据基本上存储在4个单独的文件夹中，即4个特定的类，验证也以相同的方式存储，并且效果很好.

My train data is basically stored in 4 separate folders, i.e. 4 specific classes, validation also stored in same way and works out pretty well.

因此，在我的测试文件夹中，我大约有300张图像，我要在这些图像上进行预测并制作一个数据框，如下所示:

So in my test folder I have around 300 images, on which I want to predict and make a dataframe, like this:

image_name    class
gghh.jpg       1
rrtq.png       2
1113.jpg       1
44rf.jpg       4
tyug.png       1
ssgh.jpg       3

我还使用了以下代码:

img = image.load_img(pred_dir, target_size=(28, 28))
img_tensor = image.img_to_array(img)
img_tensor = np.expand_dims(img_tensor, axis=0)
img_tensor /= 255.

cnn.predict(img_tensor)

但我收到此错误:[Errno 13] Permission denied: 'D:\\Datasets\\Trell\\images\\new_images\\testing'

但是我无法在测试图像上显示predict_generator.因此，如何使用Keras对新图像进行预测.我在Google上搜索了很多，也在Kaggle Kernels上进行了搜索，但仍未找到解决方案.

But I haven't been able to predict_generator on my test images. So how can I predict on my new images using Keras. I have googled a lot, searched on Kaggle Kernels also but haven't been able to get a solution.

推荐答案

因此，首先，应将测试图像放置在测试文件夹内的单独文件夹中.因此，在我的情况下，我在test文件夹中创建了另一个文件夹，并将其命名为all_classes. 然后运行以下代码:

So first of all the test images should be placed inside a separate folder inside the test folder. So in my case I made another folder inside test folder and named it all_classes. Then ran the following code:

test_generator = test_datagen.flow_from_directory(
    directory=pred_dir,
    target_size=(28, 28),
    color_mode="rgb",
    batch_size=32,
    class_mode=None,
    shuffle=False
)

上面的代码给了我一个输出:

The above code gives me an output:

找到306个属于1类的图像

Found 306 images belonging to 1 class

最重要的是，您必须编写以下代码:

And most importantly you've to write the following code:

test_generator.reset()

其他奇怪的输出将会出现. 然后使用.predict_generator()函数:

else weird outputs will come. Then using the .predict_generator() function:

pred=cnn.predict_generator(test_generator,verbose=1,steps=306/batch_size)

运行上面的代码将给出概率输出，因此首先我需要将其转换为类编号.在我的情况下，这是4个班级，所以班级编号分别是0、1、2和3.

Running the above code will give output in probabilities so at first I need to convert them to class number. In my case it was 4 classes, so class numbers were 0,1,2 and 3.

编写代码:

predicted_class_indices=np.argmax(pred,axis=1)

下一步是我想要类的名称:

Next step is I want the name of the classes:

labels = (train_generator.class_indices)
labels = dict((v,k) for k,v in labels.items())
predictions = [labels[k] for k in predicted_class_indices]

在这里，由班级编号将替换为班级名称.最后一步，如果要将其保存到csv文件中，请将其布置在数据帧中，图像名称后附有预测的类.

Where by class numbers will be replaced by the class names. One final step if you want to save it to a csv file, arrange it in a dataframe with the image names appended with the class predicted.

filenames=test_generator.filenames
results=pd.DataFrame({"Filename":filenames,
                      "Predictions":predictions})

显示您的数据框.现在一切都完成了.您将获得图像的所有预测类别.

Display your dataframe. Everything is done now. You get all the predicted class for your images.

这篇关于如何在新图像上使用.predict_generator()-Keras的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！