PIL.UnidentifiedImageError: cannot identify image file <_io.BytesIO object

I am trying to train my model (Image classification) using Tensorflow. I keep getting an error when I try to run the following cell:

    hist = model.fit(
        train_generator, 
        epochs=100,
        verbose=1,
        steps_per_epoch=steps_per_epoch,
        validation_data=valid_generator,
        validation_steps=val_steps_per_epoch).history

Error is:

Epoch 1/100
27/31 [=========================>....] - ETA: 1s - loss: 0.7309 - acc: 0.6181
---------------------------------------------------------------------------
UnknownError                              Traceback (most recent call last)
<ipython-input-36-b1c104100211> in <module>
      2 val_steps_per_epoch = np.ceil(valid_generator.samples/valid_generator.batch_size)
      3 
----> 4 hist = model.fit(
      5     train_generator,
      6     epochs=100,

/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
   1098                 _r=1):
   1099               callbacks.on_train_batch_begin(step)
-> 1100               tmp_logs = self.train_function(iterator)
   1101               if data_handler.should_sync:
   1102                 context.async_wait()

/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
    826     tracing_count = self.experimental_get_tracing_count()
    827     with trace.Trace(self._name) as tm:
--> 828       result = self._call(*args, **kwds)
    829       compiler = "xla" if self._experimental_compile else "nonXla"
    830       new_tracing_count = self.experimental_get_tracing_count()

/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
    853       # In this case we have created variables on the first call, so we run the
    854       # defunned version which is guaranteed to never create variables.
--> 855       return self._stateless_fn(*args, **kwds)  # pylint: disable=not-callable
    856     elif self._stateful_fn is not None:
    857       # Release the lock early so that multiple threads can perform the call

/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in __call__(self, *args, **kwargs)
   2940       (graph_function,
   2941        filtered_flat_args) = self._maybe_define_function(args, kwargs)
-> 2942     return graph_function._call_flat(
   2943         filtered_flat_args, captured_inputs=graph_function.captured_inputs)  # pylint: disable=protected-access
   2944 

/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
   1916         and executing_eagerly):
   1917       # No tape is watching; skip to running the function.
-> 1918       return self._build_call_outputs(self._inference_function.call(
   1919           ctx, args, cancellation_manager=cancellation_manager))
   1920     forward_backward = self._select_forward_and_backward_functions(

/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in call(self, ctx, args, cancellation_manager)
    553       with _InterpolateFunctionError(self):
    554         if cancellation_manager is None:
--> 555           outputs = execute.execute(
    556               str(self.signature.name),
    557               num_outputs=self._num_outputs,

/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
     57   try:
     58     ctx.ensure_initialized()
---> 59     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
     60                                         inputs, attrs, num_outputs)
     61   except core._NotOkStatusException as e:

UnknownError:  UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7fc88d55c9a0>
Traceback (most recent call last):

  File "/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/ops/script_ops.py", line 249, in __call__
    ret = func(*args)

  File "/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/autograph/impl/api.py", line 620, in wrapper
    return func(*args, **kwargs)

  File "/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 891, in generator_py_func
    values = next(generator_state.get_iterator(iterator_id))

  File "/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/data_adapter.py", line 807, in wrapped_generator
    for data in generator_fn():

  File "/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/data_adapter.py", line 933, in generator_fn
    yield x[i]

  File "/opt/anaconda3/lib/python3.8/site-packages/keras_preprocessing/image/iterator.py", line 65, in __getitem__
    return self._get_batches_of_transformed_samples(index_array)

  File "/opt/anaconda3/lib/python3.8/site-packages/keras_preprocessing/image/iterator.py", line 227, in _get_batches_of_transformed_samples
    img = load_img(filepaths[j],

  File "/opt/anaconda3/lib/python3.8/site-packages/keras_preprocessing/image/utils.py", line 114, in load_img
    img = pil_image.open(io.BytesIO(f.read()))

  File "/opt/anaconda3/lib/python3.8/site-packages/PIL/Image.py", line 2943, in open
    raise UnidentifiedImageError(

PIL.UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7fc88d55c9a0>


     [[{{node PyFunc}}]]
     [[IteratorGetNext]] [Op:__inference_train_function_24233]

Function call stack:
train_function

I tried changing from loss=’categorical_crossentropy’ to loss=’binary_crossentropy’ but still the issue persists. I wish to train the model but the Epoch keeps getting stuck.

Edit:

The train generator function and where it is used is as follows:

IMAGE_SHAPE = (224, 224)
TRAINING_DATA_DIR = str(data_root)


datagen_kwargs = dict(rescale=1./255, validation_split=.20)
valid_datagen = tf.keras.preprocessing.image.ImageDataGenerator(**datagen_kwargs)
valid_generator = valid_datagen.flow_from_directory(
    TRAINING_DATA_DIR, 
    subset="validation", 
    shuffle=True,
    target_size=IMAGE_SHAPE
)

train_datagen = tf.keras.preprocessing.image.ImageDataGenerator(**datagen_kwargs)
train_generator = train_datagen.flow_from_directory(
    TRAINING_DATA_DIR, 
    subset="training",
    shuffle=True,
    target_size=IMAGE_SHAPE)


for image_batch, label_batch in train_generator:
  break
image_batch.shape, label_batch.shape

Output: ((32, 224, 224, 3), (32, 2))

print (train_generator.class_indices)

labels = 'n'.join(sorted(train_generator.class_indices.keys()))

with open('labels.txt', 'w') as f:
  f.write(labels)

Output: {‘off’: 0, ‘on’: 1}

Answer

There was an issue with one of the img that was causing an issue and was pointed out by @Lescurel. To view the img you can run the following:

import PIL
from pathlib import Path
from PIL import UnidentifiedImageError

path = Path("INSERT PATH HERE").rglob("*.jpeg")
for img_p in path:
    try:
        img = PIL.Image.open(img_p)
    except PIL.UnidentifiedImageError:
            print(img_p)

You can also do the same for png or other formats. If there is an issue with your image, it will list it as soon as you run it