Question

对于多尺度CNN模型，我的数据集包含10个类，每个2880张图像。 Keras生成器在训练模型时不能有效地协同工作。

如何使用图像及其标签创建npz文件。

def get_training_data(datafolder):
        print("Loading training data...")

        training_data = []
        #Finds all files in datafolder
        filenames = os.listdir(datafolder)
        for filename in tqdm(filenames):
            #Combines folder name and file name.
            path = os.path.join(datafolder,filename)
            #Opens an image as an Image object.
            image = Image.open(path)
            #Resizes to a desired size.
            image = image.resize((image_width,image_height),)
            #Creates an array of pixel values from the image.
            pixel_array = np.asarray(image)

            training_data.append(pixel_array)

        #training_data is converted to a numpy array
        training_data = np.reshape(training_data,(-1,image_width,image_height,channels))
        return training_data 
image_width=800
image_height=800
channels=3
x=get_training_data("/content/drive/My Drive/DL_2_Dataset/data/Week1")
x2=get_training_data("/content/drive/My Drive/DL_2_Dataset/data/Week1")

以上代码用于从dir创建numpy数组，和

np.savez_compressed('new', week1=x, week2=x2)````


Saved into npz file,how to load labels for images ?

创建带有图像和CNN相应标签的npz文件？

0 个答案: