类型错误：“str”对象不是迭代器

Question

I am trying to run a basic CNN on using macOS Anaconda. All Keras ati is up to date (atleast i think so, but im sure it is)

I am able to run everything except for when i need to run this line,

classifier.fit_generator('training_set',
                     steps_per_epoch = 8000,
                     epochs = 25,
                     validation_data = test_set

When i attempt to run that i get the error,

TypeError: 'str' object is not an iterator

This is my code,

# Importing the Keras libraries and packages
from keras.models import Sequential
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense

# Initialising the CNN
classifier = Sequential()

# Step 1 - Convolution
classifier.add(Conv2D(32, (3, 3), input_shape = (64, 64, 3), activation = 'relu'))

# Step 2 - Pooling
classifier.add(MaxPooling2D(pool_size = (2, 2)))

# Adding a second convolutional layer
classifier.add(Conv2D(32, (3, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (2, 2)))

# Step 3 - Flattening
classifier.add(Flatten())

# Step 4 - Full connection
classifier.add(Dense(units = 128, activation = 'relu'))
classifier.add(Dense(units = 1, activation = 'sigmoid'))

# Compiling the CNN
classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])

# Part 2 - Fitting the CNN to the images

from keras.preprocessing.image import ImageDataGenerator

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('/Users/Dan/Desktop/CNN/dataset/training_set',
                                                 target_size = (64, 64),
                                                 batch_size = 32,
                                                 class_mode = 'binary')

test_set = test_datagen.flow_from_directory('/Users/Dan/Desktop/CNN/dataset/test_set',
                                            target_size = (64, 64),
                                            batch_size = 32,
                                            class_mode = 'binary')

classifier.fit_generator('training_set',
                         steps_per_epoch = 8000,
                         epochs = 25,
                         validation_data = test_set,
                         validation_steps = 2000)

# Saving Weights
weights = classifier.save_weights

"""
Single Prediction
"""
import numpy as np
from keras.preprocessing import image


test_image = image.load_img(('dataset/predictions/cat_or_dog_2.jpg'), target_size=(64, 64))
test_image = image.img_to_array(test_image)
test_image = np.expand_dims(test_image, axis = 0)
result = classifier.predict(test_image)
training_set.class_indices
if result[0][0] == 1:
    prediction = 'Dog'
else:
    prediction = 'Cat'

And this is the code itself running up to the error,

from keras.models import Sequential
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense

# Initialising the CNN
classifier = Sequential()

# Step 1 - Convolution
classifier.add(Conv2D(32, (3, 3), input_shape = (64, 64, 3), activation = 'relu'))

# Step 2 - Pooling
classifier.add(MaxPooling2D(pool_size = (2, 2)))

# Adding a second convolutional layer
classifier.add(Conv2D(32, (3, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (2, 2)))

# Step 3 - Flattening
classifier.add(Flatten())

# Step 4 - Full connection
classifier.add(Dense(units = 128, activation = 'relu'))
classifier.add(Dense(units = 1, activation = 'sigmoid'))

# Compiling the CNN
classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
Using TensorFlow backend.
2019-11-25 19:39:19.093497: I tensorflow/core/platform/cpu_feature_guard.cc:145] This TensorFlow binary is optimized with Intel(R) MKL-DNN to use the following CPU instructions in performance critical operations:  SSE4.1 SSE4.2 AVX AVX2 FMA
To enable them in non-MKL-DNN operations, rebuild TensorFlow with the appropriate compiler flags.
2019-11-25 19:39:19.095093: I tensorflow/core/common_runtime/process_util.cc:115] Creating new thread pool with default inter op setting: 4. Tune using inter_op_parallelism_threads for best performance.

from keras.preprocessing.image import ImageDataGenerator

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('/Users/Dan/Desktop/CNN/dataset/training_set',
                                                 target_size = (64, 64),
                                                 batch_size = 32,
                                                 class_mode = 'binary')
Found 8000 images belonging to 2 classes.

test_set = test_datagen.flow_from_directory('/Users/Dan/Desktop/CNN/dataset/test_set',
                                            target_size = (64, 64),
                                            batch_size = 32,
                                            class_mode = 'binary')
Found 2000 images belonging to 2 classes.

classifier.fit_generator('training_set',
                         steps_per_epoch = 8000,
                         epochs = 25,
                         validation_data = test_set,
                         validation_steps = 2000)
Epoch 1/25
Traceback (most recent call last):

  File "<ipython-input-7-e4696e5027ff>", line 5, in <module>
    validation_steps = 2000)

  File "/Users/Dan/opt/anaconda3/lib/python3.7/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)

  File "/Users/Dan/opt/anaconda3/lib/python3.7/site-packages/keras/engine/training.py", line 1732, in fit_generator
    initial_epoch=initial_epoch)

  File "/Users/Dan/opt/anaconda3/lib/python3.7/site-packages/keras/engine/training_generator.py", line 185, in fit_generator
    generator_output = next(output_generator)

  File "/Users/Dan/opt/anaconda3/lib/python3.7/site-packages/keras/utils/data_utils.py", line 742, in get
    six.reraise(*sys.exc_info())

  File "/Users/Dan/opt/anaconda3/lib/python3.7/site-packages/six.py", line 696, in reraise
    raise value

  File "/Users/Dan/opt/anaconda3/lib/python3.7/site-packages/keras/utils/data_utils.py", line 711, in get
    inputs = future.get(timeout=30)

  File "/Users/Dan/opt/anaconda3/lib/python3.7/multiprocessing/pool.py", line 657, in get
    raise self._value

  File "/Users/Dan/opt/anaconda3/lib/python3.7/multiprocessing/pool.py", line 121, in worker
    result = (True, func(*args, **kwds))

  File "/Users/Dan/opt/anaconda3/lib/python3.7/site-packages/keras/utils/data_utils.py", line 650, in next_sample
    return six.next(_SHARED_SEQUENCES[uid])

TypeError: 'str' object is not an iterator

Is there something i am missing? or a line that is wrong because im sure everything is correct.

Answer 1

You are passing a string as a first argument, you want to pass the training_set variable.

classifier.fit_generator(training_set,
                         steps_per_epoch = 8000,
                         epochs = 25,
                         validation_data = test_set,
                         validation_steps = 2000)

Answer 2

Not familiar with the package, but checking the documentation it shows that training_set should be a generator:

generator: A generator or an instance of Sequence (keras.utils.Sequence) object in order to avoid duplicate data when using multiprocessing. The output of the generator must be either a tuple (inputs, targets) a tuple (inputs, targets, sample_weights). This tuple (a single output of the generator) makes a single batch. Therefore, all arrays in this tuple must have the same length (equal to the size of this batch). Different batches may have different sizes. For example, the last batch of the epoch is commonly smaller than the others, if the size of the dataset is not divisible by the batch size. The generator is expected to loop over its data indefinitely. An epoch finishes when steps_per_epoch batches have been seen by the model.

But you are using a string with value 'training_set', I'm guessing you mean training_set (without quotes). https://keras.io/models/sequential/