search

mvoelk / ssd_detectors

SSD-based object and text detection with Keras, SSD, DSOD, TextBoxes, SegLink, TextBoxes++, CRNN
MIT License
302 stars 85 forks source link

While training, got <UnknownError: AttributeError: 'NoneType' object has no attribute 'shape'> #56

Closed pai-dy closed 3 years ago

pai-dy commented 3 years ago

Hi, Thank you for your last response. After I solved data related issue, I got another issue while training

After first epoch, I got an error like below. I tried to change batch size but I think it didn't work.

Do you have any idea?

my tf version is 2.3.1 and my current state is as below.

training image = 90729 (train:val = 0.8:0.2) initial_epoch = 0 epochs = 20 batch_size = 8

inputs, data = gt_util.sample_batch(1,0) inputs.shape, data[0] ->((1, 300, 300, 3), array([[ 0.43576389, 0.24691358, 0.59114583, 0.77777778, 24. ]]))

스크린샷 2020-12-08 오후 12 31 12

UnknownError Traceback (most recent call last) ~/.local/lib/python3.6/site-packages/tensorflow/python/eager/context.py in execution_mode(mode) 2101 ctx.executor = executor_new -> 2102 yield 2103 finally:

~/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/iterator_ops.py in _next_internal(self) 757 output_types=self._flat_output_types, --> 758 output_shapes=self._flat_output_shapes) 759

~/.local/lib/python3.6/site-packages/tensorflow/python/ops/gen_dataset_ops.py in iterator_get_next(iterator, output_types, output_shapes, name) 2609 except _core._NotOkStatusException as e: -> 2610 _ops.raise_from_not_ok_status(e, name) 2611 except _core._FallbackException:

~/.local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in raise_from_not_ok_status(e, name) 6842 # pylint: disable=protected-access -> 6843 six.raise_from(core._status_to_exception(e.code, message), None) 6844 # pylint: enable=protected-access

~/.local/lib/python3.6/site-packages/six.py in raise_from(value, from_value)

UnknownError: AttributeError: 'NoneType' object has no attribute 'shape' Traceback (most recent call last):

File "/home/user/.local/lib/python3.6/site-packages/tensorflow/python/ops/script_ops.py", line 242, in call return func(device, token, args)

File "/home/user/.local/lib/python3.6/site-packages/tensorflow/python/ops/script_ops.py", line 131, in call ret = self._func(*args)

File "/home/user/.local/lib/python3.6/site-packages/tensorflow/python/autograph/impl/api.py", line 302, in wrapper return func(*args, **kwargs)

File "/home/user/daejeon/ssd/ssd_data.py", line 519, in get_sample img_tmp, y_tmp = self.random_sized_crop(img, y)

File "/home/user/daejeon/ssd/ssd_data.py", line 441, in random_sized_crop img_h, img_w = img.shape[:2]

AttributeError: 'NoneType' object has no attribute 'shape'

 [[{{node EagerPyFunc}}]] [Op:IteratorGetNext]

During handling of the above exception, another exception occurred:

UnknownError Traceback (most recent call last)

in 53 54 for i in tqdm(range(gen_train.num_batches), 'training', leave=True): ---> 55 x, y_true = next(iterator_train) 56 metric_values = step(x, y_true, training=True) 57 metric_util.update(metric_values, training=True) ~/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/iterator_ops.py in __next__(self) 734 735 def __next__(self): # For Python 3 compatibility --> 736 return self.next() 737 738 def _next_internal(self): ~/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/iterator_ops.py in next(self) 770 def next(self): 771 try: --> 772 return self._next_internal() 773 except errors.OutOfRangeError: 774 raise StopIteration ~/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/iterator_ops.py in _next_internal(self) 762 return self._element_spec._from_compatible_tensor_list(ret) # pylint: disable=protected-access 763 except AttributeError: --> 764 return structure.from_compatible_tensor_list(self._element_spec, ret) 765 766 @property /usr/lib/python3.6/contextlib.py in __exit__(self, type, value, traceback) 97 value = type() 98 try: ---> 99 self.gen.throw(type, value, traceback) 100 except StopIteration as exc: 101 # Suppress StopIteration *unless* it's the same exception that ~/.local/lib/python3.6/site-packages/tensorflow/python/eager/context.py in execution_mode(mode) 2103 finally: 2104 ctx.executor = executor_old -> 2105 executor_new.wait() 2106 2107 ~/.local/lib/python3.6/site-packages/tensorflow/python/eager/executor.py in wait(self) 65 def wait(self): 66 """Waits for ops dispatched in this executor to finish.""" ---> 67 pywrap_tfe.TFE_ExecutorWaitForAllPendingNodes(self._handle) 68 69 def clear_error(self): UnknownError: AttributeError: 'NoneType' object has no attribute 'shape' Traceback (most recent call last): File "/home/user/.local/lib/python3.6/site-packages/tensorflow/python/ops/script_ops.py", line 242, in __call__ return func(device, token, args) File "/home/user/.local/lib/python3.6/site-packages/tensorflow/python/ops/script_ops.py", line 131, in __call__ ret = self._func(*args) File "/home/user/.local/lib/python3.6/site-packages/tensorflow/python/autograph/impl/api.py", line 302, in wrapper return func(*args, **kwargs) File "/home/user/daejeon/ssd/ssd_data.py", line 519, in get_sample img_tmp, y_tmp = self.random_sized_crop(img, y) File "/home/user/daejeon/ssd/ssd_data.py", line 441, in random_sized_crop img_h, img_w = img.shape[:2] AttributeError: 'NoneType' object has no attribute 'shape' [[{{node EagerPyFunc}}]]
mvoelk commented 3 years ago

When the image is None, it probably was not found or cannot be read ...