CODEWITHSUNDEEP
kerasimage-segmentationunet-neural-network
Ashley
Ashley

Reputation: 21

Sequential model error in unet keras image segmentation

I'm currently learning U net and i am trying to run the example code from: https://colab.research.google.com/github/keras-team/keras-io/blob/master/examples/vision/ipynb/oxford_pets_image_segmentation.ipynb#scrollTo=ge5jm8VSD_bs However, I got an error in "augmented_train_ds", and not sure how to fix this:

augmented_train_ds = (
    train_ds.shuffle(BATCH_SIZE * 2)
    .map(augment_fn, num_parallel_calls=AUTOTUNE)
    .batch(BATCH_SIZE)
    .map(unpackage_inputs)
    .prefetch(buffer_size=tf.data.AUTOTUNE)
)

And The error shows as below:

WARNING:tensorflow:Layers in a Sequential model should only have a single input tensor. Received: inputs={'images': <tf.Tensor 'args_0:0' shape=(None, None, 3) dtype=float32>, 'segmentation_masks': <tf.Tensor 'args_1:0' shape=(None, None, 1) dtype=uint8>}. Consider rewriting this model with the Functional API.
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-11-e2034c8f5b68> in <cell line: 2>()
      1 augmented_train_ds = (
----> 2     train_ds.shuffle(BATCH_SIZE * 2)
      3     .map(augment_fn, num_parallel_calls=AUTOTUNE)
      4     .batch(BATCH_SIZE)
      5     .map(unpackage_inputs)

25 frames
/usr/local/lib/python3.10/dist-packages/keras_cv/layers/preprocessing/random_choice.py in tf___augment(self, inputs, *args, **kwargs)
     12                 try:
     13                     do_return = True
---> 14                     retval_ = ag__.converted_call(ag__.ld(tf).switch_case, (), dict(branch_index=ag__.ld(selected_op), branch_fns=ag__.ld(branch_fns), default=ag__.autograph_artifact(lambda : ag__.ld(inputs))), fscope)
     15                 except:
     16                     do_return = False

TypeError: Exception encountered when calling layer 'rand_augment' (type RandAugment).

in user code:

    File "/usr/local/lib/python3.10/dist-packages/keras_cv/layers/preprocessing/base_image_augmentation_layer.py", line 419, in call  *
        outputs = self._format_output(self._augment(inputs), metadata)
    File "/usr/local/lib/python3.10/dist-packages/keras_cv/layers/preprocessing/rand_augment.py", line 127, in _augment  *
        result = super()._augment(sample)
    File "/usr/local/lib/python3.10/dist-packages/keras_cv/layers/preprocessing/random_augmentation_pipeline.py", line 103, in _augment  *
        result = tf.cond(
    File "/usr/local/lib/python3.10/dist-packages/keras/utils/traceback_utils.py", line 70, in error_handler
        raise e.with_traceback(filtered_tb) from None
    File "/tmp/__autograph_generated_fileuxkhl0zq.py", line 46, in tf__call
        ag__.if_stmt(ag__.ld(images).shape.rank == 3, if_body_1, else_body_1, get_state_1, set_state_1, ('outputs',), 1)
    File "/tmp/__autograph_generated_fileuxkhl0zq.py", line 24, in if_body_1
        outputs = ag__.converted_call(ag__.ld(self)._format_output, (ag__.converted_call(ag__.ld(self)._augment, (ag__.ld(inputs),), None, fscope), ag__.ld(metadata)), None, fscope)
    File "/tmp/__autograph_generated_filef0m6xu7q.py", line 14, in tf___augment
        retval_ = ag__.converted_call(ag__.ld(tf).switch_case, (), dict(branch_index=ag__.ld(selected_op), branch_fns=ag__.ld(branch_fns), default=ag__.autograph_artifact(lambda : ag__.ld(inputs))), fscope)

    TypeError: Exception encountered when calling layer 'random_choice' (type RandomChoice).
    
    in user code:
    
        File "/usr/local/lib/python3.10/dist-packages/keras_cv/layers/preprocessing/base_image_augmentation_layer.py", line 419, in call  *
            outputs = self._format_output(self._augment(inputs), metadata)
        File "/usr/local/lib/python3.10/dist-packages/keras_cv/layers/preprocessing/random_choice.py", line 110, in _augment  *
            default=lambda: inputs,
    
        TypeError: branches[0] and branches[1] arguments to tf.switch_case must have the same number, type, and overall structure of return values.
        
        branches[0] output: {'images': <tf.Tensor 'sequential/rand_augment/cond/random_choice/switch_case/indexed_case/Identity:0' shape=(160, 160, 3) dtype=float32>, 'segmentation_masks': <tf.Tensor 'sequential/rand_augment/cond/random_choice/switch_case/indexed_case/Identity_1:0' shape=(160, 160, 1) dtype=float32>}
        branches[1] output: {'images': <tf.Tensor 'sequential/rand_augment/cond/random_choice/switch_case/indexed_case/Identity:0' shape=(160, 160, 3) dtype=float32>, 'segmentation_masks': <tf.Tensor 'sequential/rand_augment/cond/random_choice/switch_case/indexed_case/Identity_1:0' shape=(160, 160, 1) dtype=int64>}
        
        Error details:
        Tensor("sequential/rand_augment/cond/random_choice/switch_case/indexed_case/Identity_1:0", shape=(160, 160, 1), dtype=float32) and Tensor("sequential/rand_augment/cond/random_choice/switch_case/indexed_case/Identity_1:0", shape=(160, 160, 1), dtype=int64) have different types
    
    
    Call arguments received by layer 'random_choice' (type RandomChoice):
      • inputs={'images': 'tf.Tensor(shape=(160, 160, 3), dtype=float32)', 'segmentation_masks': 'tf.Tensor(shape=(160, 160, 1), dtype=int64)'}


Call arguments received by layer 'rand_augment' (type RandAugment):
  • inputs={'images': 'tf.Tensor(shape=(160, 160, 3), dtype=float32)', 'segmentation_masks': 'tf.Tensor(shape=(160, 160, 1), dtype=int64)'}

Please help me with an example and explanation.

Upvotes: 2

Views: 204

Answers (1)

n0dus
n0dus

Reputation: 165

Okay, as far as I can see from the documentation at Torchvision, RandAugment relies an the image being uint8, whereas the images at that point are dfloat32. Therefore, the code given in the tutorial could have never worked.

I have just commented out the respective lines:

#keras_cv.layers.RandAugment(
#             value_range=(0, 1),
#             geometric=False,
#         ),

The tutorial then still works just without the additional augmentation.

Upvotes: 0

Related Questions