Unknown error: Graph execution error

Gayathri · April 10, 2024, 3:24am

I’m running into this error while training the model. Couldn’t find any resources online on how to solve it.

Link to the complete code - Colab link

this is the error message -
Epoch 1/100
1/1 [==============================] - 2s 2s/step
Original: set white with c seven again
Prediction: la e e e on

Original: place blue in o six please
Prediction: la e e e o o

450/450 [==============================] - 915s 2s/step - loss: 84.2043 - val_loss: 70.6985 - lr: 1.0000e-04
Epoch 2/100
450/450 [==============================] - ETA: 0s - loss: 71.3770

UnknownError Traceback (most recent call last)
in <cell line: 1>()
----> 1 model.fit(train, validation_data=test, epochs=100, callbacks=[checkpoint_callback, schedule_callback, example_callback])

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)
51 try:
52 ctx.ensure_initialized()
—> 53 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
54 inputs, attrs, num_outputs)
55 except core._NotOkStatusException as e:

UnknownError: Graph execution error:

Detected at node EagerPyFunc defined at (most recent call last):

Detected at node EagerPyFunc defined at (most recent call last):

2 root error(s) found.
(0) UNKNOWN: InvalidArgumentError: {{function_node _wrapped__Reshape_device/job:localhost/replica:0/task:0/device:GPU:0}} Input to reshape is a tensor with 311040 values, but the requested shape has 3 [Op:Reshape]
Traceback (most recent call last):

File “/usr/local/lib/python3.10/dist-packages/tensorflow/python/ops/script_ops.py”, line 268, in call
return func(device, token, args)

File “/usr/local/lib/python3.10/dist-packages/tensorflow/python/ops/script_ops.py”, line 146, in call
outputs = self._call(device, args)

File “/usr/local/lib/python3.10/dist-packages/tensorflow/python/ops/script_ops.py”, line 153, in _call
ret = self._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 “”, line 8, in load_data
frames = load_video(video_path)

File “”, line 8, in load_video
frame = tf.image.rgb_to_grayscale(frame)

File “/usr/local/lib/python3.10/dist-packages/tensorflow/python/util/traceback_utils.py”, line 153, in error_handler
raise e.with_traceback(filtered_tb) from None

File “/usr/local/lib/python3.10/dist-packages/tensorflow/python/eager/execute.py”, line 53, in quick_execute
tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,

tensorflow.python.framework.errors_impl.InvalidArgumentError: {{function_node _wrapped__Reshape_device/job:localhost/replica:0/task:0/device:GPU:0}} Input to reshape is a tensor with 311040 values, but the requested shape has 3 [Op:Reshape]

 [[{{node EagerPyFunc}}]]
 [[IteratorGetNext]]
 [[CTCLoss/Shape_3/_4]]

(1) UNKNOWN: InvalidArgumentError: {{function_node _wrapped__Reshape_device/job:localhost/replica:0/task:0/device:GPU:0}} Input to reshape is a tensor with 311040 values, but the requested shape has 3 [Op:Reshape]
Traceback (most recent call last):