It errors while fit the detector or generator randomly in colab(about 0.3% possibility in 1 epoch)
maybe it is a version error of Tensorflow? I searched and it is related in the input format is not np.array....(?)
If I reduce the epoch, it works entirely... but I want to train a large epoch... and I want to ask about this random error If reproducible in my sharable colab link...
318/1000 [========>.....................] - ETA: 16:05 - loss: 0.0054
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-13-4e1d29ce0729> in <module>()
13 validation_data=detection_val_generator,
14 #validation_steps=math.ceil(len(background_splits[1]) / detector_batch_size)
---> 15 validation_steps=100
16 )
10 frames
/usr/local/lib/python3.6/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:
InvalidArgumentError: 2 root error(s) found.
(0) Invalid argument: AxisError: axis 1 is out of bounds for array of dimension 1
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/script_ops.py", line 244, in __call__
ret = func(*args)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/autograph/impl/api.py", line 302, in wrapper
return func(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/data/ops/dataset_ops.py", line 827, in generator_py_func
values = next(generator_state.get_iterator(iterator_id))
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/data_adapter.py", line 814, in wrapped_generator
for data in generator_fn():
File "/usr/local/lib/python3.6/dist-packages/keras_ocr/detection.py", line 631, in get_batch_generator
batch = [next(image_generator) for n in range(batch_size)]
File "/usr/local/lib/python3.6/dist-packages/keras_ocr/detection.py", line 631, in <listcomp>
batch = [next(image_generator) for n in range(batch_size)]
File "/usr/local/lib/python3.6/dist-packages/keras_ocr/data_generation.py", line 577, in get_image_generator
draw_contour=draw_contour_text)
File "/usr/local/lib/python3.6/dist-packages/keras_ocr/data_generation.py", line 351, in draw_text_image
min_character_size = character_sizes.sum(axis=1).min()
File "/usr/local/lib/python3.6/dist-packages/numpy/core/_methods.py", line 38, in _sum
return umr_sum(a, axis, dtype, out, keepdims, initial, where)
numpy.AxisError: axis 1 is out of bounds for array of dimension 1
[[{{node PyFunc}}]]
[[IteratorGetNext]]
(1) Invalid argument: AxisError: axis 1 is out of bounds for array of dimension 1
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/script_ops.py", line 244, in __call__
ret = func(*args)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/autograph/impl/api.py", line 302, in wrapper
return func(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/data/ops/dataset_ops.py", line 827, in generator_py_func
values = next(generator_state.get_iterator(iterator_id))
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/data_adapter.py", line 814, in wrapped_generator
for data in generator_fn():
File "/usr/local/lib/python3.6/dist-packages/keras_ocr/detection.py", line 631, in get_batch_generator
batch = [next(image_generator) for n in range(batch_size)]
File "/usr/local/lib/python3.6/dist-packages/keras_ocr/detection.py", line 631, in <listcomp>
batch = [next(image_generator) for n in range(batch_size)]
File "/usr/local/lib/python3.6/dist-packages/keras_ocr/data_generation.py", line 577, in get_image_generator
draw_contour=draw_contour_text)
File "/usr/local/lib/python3.6/dist-packages/keras_ocr/data_generation.py", line 351, in draw_text_image
min_character_size = character_sizes.sum(axis=1).min()
File "/usr/local/lib/python3.6/dist-packages/numpy/core/_methods.py", line 38, in _sum
return umr_sum(a, axis, dtype, out, keepdims, initial, where)
numpy.AxisError: axis 1 is out of bounds for array of dimension 1
[[{{node PyFunc}}]]
[[IteratorGetNext]]
[[IteratorGetNext/_7]]
0 successful operations.
0 derived errors ignored. [Op:__inference_train_function_10153]
Function call stack:
train_function -> train_function
I'm using google colab and it errors in training(fit)
numpy.AxisError: axis 1 is out of bounds for array of dimension 1
And my colab file link(reproducible) is : https://colab.research.google.com/drive/1AmQzQiHghCi_Lnxf3hcZKUsuewtPMRlg?usp=sharingIt errors while fit the detector or generator randomly in colab(about 0.3% possibility in 1 epoch) maybe it is a version error of Tensorflow? I searched and it is related in the input format is not np.array....(?) If I reduce the epoch, it works entirely... but I want to train a large epoch... and I want to ask about this random error If reproducible in my sharable colab link...
thank you.
and