TypeError: listdir: path should be string, bytes, os.PathLike or None, not DirectoryIterator

Question

im beginner on Machine learning and currently trying to apply VGG net for my neural network

Im facing this kind of error which is

listdir: path should be string, bytes, os.PathLike or None, not ImageDataGenerator

Im currently use Jupyter notebook as editor and here is my code that i faced error

from tensorflow.keras.preprocessing.image import ImageDataGenerator
#Training Set
train_set = train_datagen.flow_from_directory('train')

#Training Set
valid_set = train_datagen.flow_from_directory('test')


train_size, validation_size, test_size = 200, 100, 100
img_width, img_height = 224, 224  # Default input size for VGG16

# Extract features
import os, shutil


datagen = ImageDataGenerator(rescale=1./255)
batch_size = 32

def extract_features(directory, sample_count):
    features = np.zeros(shape=(sample_count, 7, 7, 512))  # Must be equal to the output of the convolutional base
    labels = np.zeros(shape=(sample_count))
    # Preprocess data
    generator = datagen.flow_from_directory(directory,
                                            target_size=(img_width,img_height),
                                            batch_size = batch_size,
                                            class_mode='categorical')
    # Pass data through convolutional base
    i = 0
    for inputs_batch, labels_batch in generator:
        features_batch = conv_base.predict(inputs_batch)
        features[i * batch_size: (i + 1) * batch_size] = features_batch
        labels[i * batch_size: (i + 1) * batch_size] = labels_batch
        i += 1
        if i * batch_size >= sample_count:
            break
    return features, labels

train_features, train_labels = extract_features(train_set, train_size)  # Agree with our small dataset size
validation_features, validation_labels = extract_features(validation_dir, validation_size)
test_features, test_labels = extract_features(test_dir, test_size)

this is the error occur

Found 714 images belonging to 10 classes. Found 100 images belonging

to 10 classes. --------------------------------------------------------------------------- TypeError Traceback (most recent call last) in 36 return features, labels 37 ---> 38 train_features, train_labels = extract_features(train_set, train_size) # Agree with our small dataset size 39 validation_features, validation_labels = extract_features(validation_dir, validation_size) 40 test_features, test_labels = extract_features(test_dir, test_size)

in extract_features(directory, sample_count) 24 target_size=(img_width,img_height), 25 batch_size = batch_size, ---> 26 class_mode='categorical') 27 # Pass data through convolutional base 28 i = 0

~\Anaconda3\envs\tensorflow_cpu\lib\site-packages\keras_preprocessing\image\image_data_generator.py in flow_from_directory(self, directory, target_size, color_mode, classes, class_mode, batch_size, shuffle, seed, save_to_dir, save_prefix, save_format, follow_links, subset, interpolation) 538 follow_links=follow_links, 539 subset=subset, --> 540 interpolation=interpolation 541 ) 542

~\Anaconda3\envs\tensorflow_cpu\lib\site-packages\keras_preprocessing\image\directory_iterator.py in init(self, directory, image_data_generator, target_size, color_mode, classes, class_mode, batch_size, shuffle, seed, data_format, save_to_dir, save_prefix, save_format, follow_links, subset, interpolation, dtype) 104 if not classes: 105 classes = [] --> 106 for subdir in sorted(os.listdir(directory)): 107 if os.path.isdir(os.path.join(directory, subdir)): 108 classes.append(subdir)

TypeError: listdir: path should be string, bytes, os.PathLike or None, not DirectoryIterator

leo leo · Accepted Answer · 2020-04-22T15:55:40

you are passing a data generator to another data generator, in this line:

generator = datagen.flow_from_directory(directory,
                                        target_size=(img_width,img_height),
                                        batch_size = batch_size,
                                        class_mode='categorical')

first argument, directory, should be a directory, not a data generator, it should be something like: 'path/to/my/train_set/' . which is just 'train' in your case I guess, since you have them in the same folder as your notebook.

TypeError: listdir: path should be string, bytes, os.PathLike or None, not DirectoryIterator

1 Answers