C2W1 Assignment error while training

Course Q&A TensorFlow Developer Professional Convolutional Neural Networks in TensorFlow
1

Hi there, I am working the assignment of week-1. But I am getting this error.

Epoch 1/15
 433/1125 [==========>...................] - ETA: 27s - loss: 0.6957 - accuracy: 0.5635
---------------------------------------------------------------------------
UnknownError                              Traceback (most recent call last)
<ipython-input-12-4fd84b04e1cf> in <cell line: 6>()
      4 # Train the model
      5 # Note that this may take some time.
----> 6 history = model.fit(train_generator,
      7                     epochs=15,
      8                     verbose=1,

1 frames
/usr/local/lib/python3.10/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
     58         for t in inputs
     59     ]
---> 60     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
     61                                         inputs, attrs, num_outputs)
     62   except core._NotOkStatusException as e:

UnknownError: Graph execution error:

Detected at node PyFunc defined at (most recent call last):
<stack traces unavailable>
Detected at node PyFunc defined at (most recent call last):
<stack traces unavailable>
2 root error(s) found.
  (0) UNKNOWN:  UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7ded78538d10>
Traceback (most recent call last):

  File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/ops/script_ops.py", line 270, in __call__
    ret = func(*args)

  File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/autograph/impl/api.py", line 643, in wrapper
    return func(*args, **kwargs)

  File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/data/ops/from_generator_op.py", line 198, in generator_py_func
    values = next(generator_state.get_iterator(iterator_id))

  File "/usr/local/lib/python3.10/dist-packages/keras/src/engine/data_adapter.py", line 917, in wrapped_generator
    for data in generator_fn():

  File "/usr/local/lib/python3.10/dist-packages/keras/src/engine/data_adapter.py", line 1064, in generator_fn
    yield x[i]

  File "/usr/local/lib/python3.10/dist-packages/keras/src/preprocessing/image.py", line 116, in __getitem__
    return self._get_batches_of_transformed_samples(index_array)

  File "/usr/local/lib/python3.10/dist-packages/keras/src/preprocessing/image.py", line 370, in _get_batches_of_transformed_samples
    img = image_utils.load_img(

  File "/usr/local/lib/python3.10/dist-packages/keras/src/utils/image_utils.py", line 423, in load_img
    img = pil_image.open(io.BytesIO(f.read()))

  File "/usr/local/lib/python3.10/dist-packages/PIL/Image.py", line 3283, in open
    raise UnidentifiedImageError(msg)

PIL.UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7ded78538d10>


	 [[{{node PyFunc}}]]
	 [[IteratorGetNext]]
	 [[IteratorGetNext/_7]]
  (1) UNKNOWN:  UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7ded78538d10>
Traceback (most recent call last):

  File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/ops/script_ops.py", line 270, in __call__
    ret = func(*args)

  File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/autograph/impl/api.py", line 643, in wrapper
    return func(*args, **kwargs)

  File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/data/ops/from_generator_op.py", line 198, in generator_py_func
    values = next(generator_state.get_iterator(iterator_id))

  File "/usr/local/lib/python3.10/dist-packages/keras/src/engine/data_adapter.py", line 917, in wrapped_generator
    for data in generator_fn():

  File "/usr/local/lib/python3.10/dist-packages/keras/src/engine/data_adapter.py", line 1064, in generator_fn
    yield x[i]

  File "/usr/local/lib/python3.10/dist-packages/keras/src/preprocessing/image.py", line 116, in __getitem__
    return self._get_batches_of_transformed_samples(index_array)

  File "/usr/local/lib/python3.10/dist-packages/keras/src/preprocessing/image.py", line 370, in _get_batches_of_transformed_samples
    img = image_utils.load_img(

  File "/usr/local/lib/python3.10/dist-packages/keras/src/utils/image_utils.py", line 423, in load_img
    img = pil_image.open(io.BytesIO(f.read()))

  File "/usr/local/lib/python3.10/dist-packages/PIL/Image.py", line 3283, in open
    raise UnidentifiedImageError(msg)

PIL.UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7ded78538d10>


	 [[{{node PyFunc}}]]
	 [[IteratorGetNext]]
0 successful operations.
0 derived errors ignored. [Op:__inference_train_function_1423]
1 Like
3

You should not consider invalid image files as part of your train / val datasets. As shown in the markdown, you should have 11249 and not 11250 images per class of training dataset.

1 Like
4

Yes, I found the error. Anyway, thank you for your reply.

5

Hey,

I am getting the same error inspite of the fact that I am ignoring the 2 empty files.

image
image901×132 5.49 KB

Is there any other solution here? I just can’t get rid of this problem.

6

Hello,

Okay I got the error, it is trivial, but maybe someone else bumps into this too. In the for cycle in which I delete the picture I used list.pop(i) instead of list.remove(f"{i}.jpg") so I deleted the 666th element from my list but that is not the 666.jpg so the empty file was still among the files I used later for training.