What is causing this Keras image processing error?

Question

I'm attempting to train a CNN but the program fails every time but in a random location. The error that's kicking up is OSError: image file is truncated (15 bytes not processed). FYI this is dealing with augmented data from a previous step. The code is below:

import os

from keras import backend as K
from keras.layers import Activation, Dense, Dropout
from keras.layers import Conv2D, Flatten, MaxPooling2D
from keras.models import Sequential
from keras.preprocessing.image import ImageDataGenerator

import matplotlib.pyplot as plt

cwd = os.getcwd()

# dimensions of our images.
img_width, img_height = 150, 150

train_data_dir = (str(cwd) + r'\augmented\train\\')
validation_data_dir = (str(cwd) + r'\augmented\validation\\')
nb_train_samples = 1000
nb_validation_samples = 500
epochs = 20
batch_size = 10

if K.image_data_format() == 'channels_first':
    input_shape = (3, img_width, img_height)
else:
    input_shape = (img_width, img_height, 3)

model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True)

# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1. / 255)

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

history = model.fit_generator(
    train_generator,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=nb_validation_samples // batch_size)

model.save_weights('chips.h5')

acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']

epochs = range(1, len(acc) + 1)

plt.plot(epochs, acc, 'bo', label='Training acc')
plt.plot(epochs, val_acc, 'b', label='Validation acc')
plt.title('Training and validation accuracy')
plt.legend()

plt.figure()

plt.plot(epochs, loss, 'bo', label='Training loss')
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.legend()

plt.show()

The CNN starts iterating but usually in epoch 2 somewhere I get this truncated image thing. All the images were augmented the same way though. Anyone have ideas?

Entire traceback is:

Traceback (most recent call last):
  File "c:\Users\Mac2\.vscode\extensions\ms-python.python-2019.3.6558\pythonFiles\ptvsd_launcher.py", line 45, in <module>
    main(ptvsdArgs)
  File "c:\Users\Mac2\.vscode\extensions\ms-python.python-2019.3.6558\pythonFiles\lib\python\ptvsd\__main__.py", line 391, in main
    run()
  File "c:\Users\Mac2\.vscode\extensions\ms-python.python-2019.3.6558\pythonFiles\lib\python\ptvsd\__main__.py", line 272, in run_file
    runpy.run_path(target, run_name='__main__')
  File "C:\Users\Mac2\Anaconda3\lib\runpy.py", line 263, in run_path
    pkg_name=pkg_name, script_name=fname)
  File "C:\Users\Mac2\Anaconda3\lib\runpy.py", line 96, in _run_module_code
    mod_name, mod_spec, pkg_name, script_name)
  File "C:\Users\Mac2\Anaconda3\lib\runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "c:\Users\Mac2\Desktop\CNN\Chips\train.py", line 119, in <module>
    validation_steps=nb_validation_samples // batch_size)
  File "C:\Users\Mac2\Anaconda3\lib\site-packages\keras\legacy\interfaces.py", lineapper
    return func(*args, **kwargs)
  File "C:\Users\Mac2\Anaconda3\lib\site-packages\keras\engine\training.py", line 1t_generator
    initial_epoch=initial_epoch)
  File "C:\Users\Mac2\Anaconda3\lib\site-packages\keras\engine\training_generator.p81, in fit_generator
    generator_output = next(output_generator)
  File "C:\Users\Mac2\Anaconda3\lib\site-packages\keras\utils\data_utils.py", linet
    six.reraise(*sys.exc_info())
  File "C:\Users\Mac2\Anaconda3\lib\site-packages\six.py", line 693, in reraise
    raise value
  File "C:\Users\Mac2\Anaconda3\lib\site-packages\keras\utils\data_utils.py", linet
    inputs = self.queue.get(block=True).get()
  File "C:\Users\Mac2\Anaconda3\lib\multiprocessing\pool.py", line 644, in get
    raise self._value
  File "C:\Users\Mac2\Anaconda3\lib\multiprocessing\pool.py", line 119, in worker
    result = (True, func(*args, **kwds))
  File "C:\Users\Mac2\Anaconda3\lib\site-packages\keras\utils\data_utils.py", linext_sample
    return six.next(_SHARED_SEQUENCES[uid])
  File "C:\Users\Mac2\Anaconda3\lib\site-packages\keras_preprocessing\image\iteratoe 100, in __next__
    return self.next(*args, **kwargs)
  File "C:\Users\Mac2\Anaconda3\lib\site-packages\keras_preprocessing\image\iteratoe 112, in next
    return self._get_batches_of_transformed_samples(index_array)
  File "C:\Users\Mac2\Anaconda3\lib\site-packages\keras_preprocessing\image\iteratoe 226, in _get_batches_of_transformed_samples
    interpolation=self.interpolation)
  File "C:\Users\Mac2\Anaconda3\lib\site-packages\keras_preprocessing\image\utils.p26, in load_img
    img = img.resize(width_height_tuple, resample)
  File "C:\Users\Mac2\Anaconda3\lib\site-packages\PIL\Image.py", line 1763, in resi    self.load()
  File "C:\Users\Mac2\Anaconda3\lib\site-packages\PIL\ImageFile.py", line 232, in l    "(%d bytes not processed)" % len(b))
OSError: image file is truncated (15 bytes not processed)

Answer 1

Your problem seems to be a different sized image, your program seems to crash due to the settings in pillow. Here is the official code of the pillow module, if you search for truncated you can see why this error can be raised. Here the highest voted answer provides code to prevent an import error with the truncated image.

Alternatively you can remove the image, here are people with your problem that simply sort out all images smaller than 50kB. Hope this helps.