error during fitting a CNN model

[devmegablaster]

Hey Daniel,
I encountered an error tonight while fitting a binary image classification model...
Here is the link to the Colab --> Notebook

(PS - Love the content! 👍🏻 )

[mrdbourke]

Hey there,

Looks like your data has an input shape problem.

InvalidArgumentError: 2 root error(s) found.
  (0) Invalid argument:  Input size should match (header_size + row_size * abs_height) but they differ by 2
	 [[{{node decode_image/DecodeImage}}]]
	 [[IteratorGetNext]]
  (1) Invalid argument:  Input size should match (header_size + row_size * abs_height) but they differ by 2
	 [[{{node decode_image/DecodeImage}}]]
	 [[IteratorGetNext]]
	 [[gradient_tape/binary_crossentropy/logistic_loss/mul/Shape_1/_4]]

What have you tried so far?

Do you know what the input shapes of your data are?

[ashikshafi08]

Hey @MEGA-BLASTER2004

I think there is an issue with your dataset itself, when I tried doing the same with a sample dataset (pizza/steak) it worked. Some of the image files in your data might be broken or corrupted.

You can try experimenting with the pizza/steak dataset we used in the course and cross-check if you want.

[devmegablaster]

Okay!
I will try with pizza_steak

[gauravreddy08]

Hey @MEGA-BLASTER2004 ,
I firstly thought that the error was with function you used : tf.keras.preprocessing.image_dataset_from_directory. So i had replaced it with tf.keras.preprocessing.image.ImageDataGenerator.flow_from_directory()

Before

After

Now that I changed it I got a new error, I guess that the problem is with the dataset itself. There's some problem with the EXIF data of images.

• If you had uploaded this dataset to Azure Cloud by yourself the problem might be there.
• If you haven't, then the problem is with dataset itself.

Epoch 1/3
181/782 [=====>........................] - ETA: 1:08 - loss: 0.1536 - accuracy: 0.9560/usr/local/lib/python3.7/dist-packages/PIL/TiffImagePlugin.py:770: UserWarning: Possibly corrupt EXIF data.  Expecting to read 32 bytes but only got 0. Skipping tag 270
  " Skipping tag %s" % (size, len(data), tag)
/usr/local/lib/python3.7/dist-packages/PIL/TiffImagePlugin.py:770: UserWarning: Possibly corrupt EXIF data.  Expecting to read 5 bytes but only got 0. Skipping tag 271
  " Skipping tag %s" % (size, len(data), tag)
/usr/local/lib/python3.7/dist-packages/PIL/TiffImagePlugin.py:770: UserWarning: Possibly corrupt EXIF data.  Expecting to read 8 bytes but only got 0. Skipping tag 272
  " Skipping tag %s" % (size, len(data), tag)
/usr/local/lib/python3.7/dist-packages/PIL/TiffImagePlugin.py:770: UserWarning: Possibly corrupt EXIF data.  Expecting to read 8 bytes but only got 0. Skipping tag 282
  " Skipping tag %s" % (size, len(data), tag)
/usr/local/lib/python3.7/dist-packages/PIL/TiffImagePlugin.py:770: UserWarning: Possibly corrupt EXIF data.  Expecting to read 8 bytes but only got 0. Skipping tag 283
  " Skipping tag %s" % (size, len(data), tag)
/usr/local/lib/python3.7/dist-packages/PIL/TiffImagePlugin.py:770: UserWarning: Possibly corrupt EXIF data.  Expecting to read 20 bytes but only got 0. Skipping tag 306
  " Skipping tag %s" % (size, len(data), tag)
/usr/local/lib/python3.7/dist-packages/PIL/TiffImagePlugin.py:770: UserWarning: Possibly corrupt EXIF data.  Expecting to read 48 bytes but only got 0. Skipping tag 532
  " Skipping tag %s" % (size, len(data), tag)
/usr/local/lib/python3.7/dist-packages/PIL/TiffImagePlugin.py:788: UserWarning: Corrupt EXIF data.  Expecting to read 2 bytes but only got 0. 
  warnings.warn(str(msg))
518/782 [==================>...........] - ETA: 30s - loss: 0.0855 - accuracy: 0.9752
---------------------------------------------------------------------------
UnknownError                              Traceback (most recent call last)
<ipython-input-19-c695cdbb0da4> in <module>()
----> 1 model_0.fit(train_data, epochs = 3, steps_per_epoch = len(train_data))

6 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
     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:
     62     if name is not None:

UnknownError: 2 root error(s) found.
  (0) Unknown:  UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7efcb28324d0>
Traceback (most recent call last):

  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/ops/script_ops.py", line 249, in __call__
    ret = func(*args)

  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/autograph/impl/api.py", line 645, in wrapper
    return func(*args, **kwargs)

  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/data/ops/dataset_ops.py", line 961, in generator_py_func
    values = next(generator_state.get_iterator(iterator_id))

  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/data_adapter.py", line 837, in wrapped_generator
    for data in generator_fn():

  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/data_adapter.py", line 963, in generator_fn
    yield x[i]

  File "/usr/local/lib/python3.7/dist-packages/keras_preprocessing/image/iterator.py", line 65, in __getitem__
    return self._get_batches_of_transformed_samples(index_array)

  File "/usr/local/lib/python3.7/dist-packages/keras_preprocessing/image/iterator.py", line 230, in _get_batches_of_transformed_samples
    interpolation=self.interpolation)

  File "/usr/local/lib/python3.7/dist-packages/keras_preprocessing/image/utils.py", line 114, in load_img
    img = pil_image.open(io.BytesIO(f.read()))

  File "/usr/local/lib/python3.7/dist-packages/PIL/Image.py", line 2896, in open
    "cannot identify image file %r" % (filename if filename else fp)

PIL.UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7efcb28324d0>


	 [[{{node PyFunc}}]]
	 [[IteratorGetNext]]
  (1) Unknown:  UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7efcb28324d0>
Traceback (most recent call last):

  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/ops/script_ops.py", line 249, in __call__
    ret = func(*args)

  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/autograph/impl/api.py", line 645, in wrapper
    return func(*args, **kwargs)

  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/data/ops/dataset_ops.py", line 961, in generator_py_func
    values = next(generator_state.get_iterator(iterator_id))

  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/data_adapter.py", line 837, in wrapped_generator
    for data in generator_fn():

  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/data_adapter.py", line 963, in generator_fn
    yield x[i]

  File "/usr/local/lib/python3.7/dist-packages/keras_preprocessing/image/iterator.py", line 65, in __getitem__
    return self._get_batches_of_transformed_samples(index_array)

  File "/usr/local/lib/python3.7/dist-packages/keras_preprocessing/image/iterator.py", line 230, in _get_batches_of_transformed_samples
    interpolation=self.interpolation)

  File "/usr/local/lib/python3.7/dist-packages/keras_preprocessing/image/utils.py", line 114, in load_img
    img = pil_image.open(io.BytesIO(f.read()))

  File "/usr/local/lib/python3.7/dist-packages/PIL/Image.py", line 2896, in open
    "cannot identify image file %r" % (filename if filename else fp)

PIL.UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7efcb28324d0>


	 [[{{node PyFunc}}]]
	 [[IteratorGetNext]]
	 [[IteratorGetNext/_4]]
0 successful operations.
0 derived errors ignored. [Op:__inference_train_function_14297]

Function call stack:
train_function -> train_function

[gauravreddy08]

And here's the link of all the changes I made

[devmegablaster]

Maybe there's an error in the dataset...I just found it on Kaggle