(isic) tong@ws5:~/isic/mura/demura/Musculoskeletal-Radiographs-Abnormality-Classifier$ python train.py --epochs 5 --b 32

Using TensorFlow backend.

tf : 1.6.0

keras : 2.2.2

numpy : 1.15.3

pandas : 0.23.4

Found 36812 images belonging to 7 classes.

Found 3197 images belonging to 7 classes.

/home/tong/isic/local/lib/python2.7/site-packages/keras/engine/training_generator.py:46: UserWarning: Using a generator with `use_multiprocessing=True` and multiple workers may duplicate your data. Please consider using the`keras.utils.Sequence class.

  UserWarning('Using a generator with `use_multiprocessing=True`'

Epoch 1/5

  93/1150 [=>............................] - ETA: 59:59 - loss: -17.0199 - binary_accuracy: 0.1579  Traceback (most recent call last):

  File "/home/tong/isic/local/lib/python2.7/site-packages/keras/utils/data_utils.py", line 677, in _data_generator_task

    generator_output = next(self._generator)

  File "/home/tong/isic/local/lib/python2.7/site-packages/keras_preprocessing/image.py", line 1822, in next

    return self._get_batches_of_transformed_samples(index_array)

  File "/home/tong/isic/local/lib/python2.7/site-packages/keras_preprocessing/image.py", line 1775, in _get_batches_of_transformed_samples

    interpolation=self.interpolation)

  File "/home/tong/isic/local/lib/python2.7/site-packages/keras_preprocessing/image.py", line 493, in load_img

    img = pil_image.open(path)

  File "/home/tong/isic/local/lib/python2.7/site-packages/PIL/Image.py", line 2622, in open

    % (filename if filename else fp))

IOError: cannot identify image file 'MURA-v1.1/train/XR_WRIST/patient07840/study2_negative/._image3.png'

  94/1150 [=>............................] - ETA: 59:58 - loss: -17.1653 - binary_accuracy: 0.1599Traceback (most recent call last):

  File "train.py", line 153, in

    train()

  File "train.py", line 149, in train

    callbacks=callbacks)

  File "/home/tong/isic/local/lib/python2.7/site-packages/keras/legacy/interfaces.py", line 91, in wrapper

    return func(*args, **kwargs)

  File "/home/tong/isic/local/lib/python2.7/site-packages/keras/engine/training.py", line 1415, in fit_generator

    initial_epoch=initial_epoch)

  File "/home/tong/isic/local/lib/python2.7/site-packages/keras/engine/training_generator.py", line 177, in fit_generator

    generator_output = next(output_generator)

  File "/home/tong/isic/local/lib/python2.7/site-packages/keras/utils/data_utils.py", line 793, in get

    six.reraise(value.__class__, value, value.__traceback__)

  File "", line 3, in reraise

IOError: cannot identify image file 'MURA-v1.1/train/XR_WRIST/patient07840/study2_negative/._image3.png'

 

 

 

 

 

(isic) tong@ws5:~/isic/mura/demura$ cd Musculoskeletal-Radiographs-Abnormality-Classifier/

(isic) tong@ws5:~/isic/mura/demura/Musculoskeletal-Radiographs-Abnormality-Classifier$ python train.py --epochs 5 --b 32

Using TensorFlow backend.

tf : 1.6.0

keras : 2.2.2

numpy : 1.15.3

pandas : 0.23.4

Found 36812 images belonging to 7 classes.

Found 3197 images belonging to 7 classes.

/home/tong/isic/local/lib/python2.7/site-packages/keras/engine/training_generator.py:46: UserWarning: Using a generator with `use_multiprocessing=True` and multiple workers may duplicate your data. Please consider using the`keras.utils.Sequence class.

  UserWarning('Using a generator with `use_multiprocessing=True`'

Epoch 1/5

858/1150 [=====================>........] - ETA: 16:29 - loss: -31.4064 - binary_accuracy: 0.2083Traceback (most recent call last):

  File "/home/tong/isic/local/lib/python2.7/site-packages/keras/utils/data_utils.py", line 677, in _data_generator_task

    generator_output = next(self._generator)

  File "/home/tong/isic/local/lib/python2.7/site-packages/keras_preprocessing/image.py", line 1822, in next

    return self._get_batches_of_transformed_samples(index_array)

  File "/home/tong/isic/local/lib/python2.7/site-packages/keras_preprocessing/image.py", line 1775, in _get_batches_of_transformed_samples

    interpolation=self.interpolation)

  File "/home/tong/isic/local/lib/python2.7/site-packages/keras_preprocessing/image.py", line 493, in load_img

    img = pil_image.open(path)

  File "/home/tong/isic/local/lib/python2.7/site-packages/PIL/Image.py", line 2622, in open

    % (filename if filename else fp))

IOError: cannot identify image file 'MURA-v1.1/train/XR_WRIST/patient07840/study2_negative/._image2.png'

859/1150 [=====================>........] - ETA: 16:26 - loss: -31.4138 - binary_accuracy: 0.2083Traceback (most recent call last):

  File "train.py", line 153, in

    train()

  File "train.py", line 149, in train

    callbacks=callbacks)

  File "/home/tong/isic/local/lib/python2.7/site-packages/keras/legacy/interfaces.py", line 91, in wrapper

    return func(*args, **kwargs)

  File "/home/tong/isic/local/lib/python2.7/site-packages/keras/engine/training.py", line 1415, in fit_generator

    initial_epoch=initial_epoch)

  File "/home/tong/isic/local/lib/python2.7/site-packages/keras/engine/training_generator.py", line 177, in fit_generator

    generator_output = next(output_generator)

  File "/home/tong/isic/local/lib/python2.7/site-packages/keras/utils/data_utils.py", line 793, in get

    six.reraise(value.__class__, value, value.__traceback__)

  File "", line 3, in reraise

IOError: cannot identify image file 'MURA-v1.1/train/XR_WRIST/patient07840/study2_negative/._image2.png'