search

uctb / UCTB

An Open Source Spatio-Temporal Prediction Package
MIT License
193 stars 43 forks source link

STMeta cannot set `st_method='GRU', gclstm_layers=2` #15

Closed Star-live closed 2 years ago

Star-live commented 2 years ago

When I run QuickStarts/STMeta.py with the st_method='GRU', gclstm_layers=2, I encountered the following error. How should I fix it?

The key error message is as follows:

tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimensions must be equal, but are 1 and 64 for 'rnn/MatMul' (op: 'MatMul') with input shapes: [?,1], [64,64].
  File "/home/zhuhang/Work/UCTB/QuickStarts/STMeta.py", line 24, in <module>
    STMeta_Obj.build()
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/UCTB/model/STMeta.py", line 192, in build
    tf.reshape(target_tensor, [-1, time_step, 1]))
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/keras/layers/recurrent.py", line 701, in __call__
    return super(RNN, self).__call__(inputs, **kwargs)

The complete error message is as follows:

Traceback (most recent call last):
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1659, in _create_c_op
    c_op = c_api.TF_FinishOperation(op_desc)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimensions must be equal, but are 1 and 64 for 'rnn/MatMul' (op: 'MatMul') with input shapes: [?,1], [64,64].

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/zhuhang/.vscode-server/extensions/ms-python.python-2022.6.3/pythonFiles/lib/python/debugpy/__main__.py", line 45, in <module>
    cli.main()
  File "/home/zhuhang/.vscode-server/extensions/ms-python.python-2022.6.3/pythonFiles/lib/python/debugpy/../debugpy/server/cli.py", line 444, in main
    run()
  File "/home/zhuhang/.vscode-server/extensions/ms-python.python-2022.6.3/pythonFiles/lib/python/debugpy/../debugpy/server/cli.py", line 285, in run_file
    runpy.run_path(target_as_str, run_name=compat.force_str("__main__"))
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/runpy.py", line 263, in run_path
    pkg_name=pkg_name, script_name=fname)
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/runpy.py", line 96, in _run_module_code
    mod_name, mod_spec, pkg_name, script_name)
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/zhuhang/Work/UCTB/QuickStarts/STMeta.py", line 24, in <module>
    STMeta_Obj.build()
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/UCTB/model/STMeta.py", line 192, in build
    tf.reshape(target_tensor, [-1, time_step, 1]))
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/keras/layers/recurrent.py", line 701, in __call__
    return super(RNN, self).__call__(inputs, **kwargs)
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py", line 554, in __call__
    outputs = self.call(inputs, *args, **kwargs)
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/keras/layers/recurrent.py", line 822, in call
    zero_output_for_mask=self.zero_output_for_mask)
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/keras/backend.py", line 3453, in rnn
    initial_states + constants)
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/keras/layers/recurrent.py", line 807, in step
    output, new_states = self.cell.call(inputs, states, **kwargs)
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/keras/layers/recurrent.py", line 137, in call
    inputs, states = cell.call(inputs, states, **kwargs)
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/keras/layers/recurrent.py", line 1544, in call
    x_z = K.dot(inputs_z, self.kernel[:, :self.units])
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/keras/backend.py", line 1463, in dot
    out = math_ops.matmul(x, y)
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 2455, in matmul
    a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 5333, in mat_mul
    name=name)
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
    op_def=op_def)
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
    return func(*args, **kwargs)
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3300, in create_op
    op_def=op_def)
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1823, in __init__
    control_input_ops)
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1662, in _create_c_op
    raise ValueError(str(e))
ValueError: Dimensions must be equal, but are 1 and 64 for 'rnn/MatMul' (op: 'MatMul') with input shapes: [?,1], [64,64].
ERROR:tensorflow:==================================
Object was never used (type <class 'tensorflow.python.ops.tensor_array_ops.TensorArray'>):
<tensorflow.python.ops.tensor_array_ops.TensorArray object at 0x7fe56dbfdf28>
If you want to mark it as used call its "mark_used()" method.
It was originally created here:
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/keras/backend.py", line 3443, in <genexpr>
    for ta, input_ in zip(input_ta, flatted_inputs))  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/util/tf_should_use.py", line 193, in wrapped
    return _add_should_use_warning(fn(*args, **kwargs))
==================================
ERROR:tensorflow:==================================
Object was never used (type <class 'tensorflow.python.ops.tensor_array_ops.TensorArray'>):
<tensorflow.python.ops.tensor_array_ops.TensorArray object at 0x7fe56dbfdcf8>
If you want to mark it as used call its "mark_used()" method.
It was originally created here:
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/keras/backend.py", line 3443, in <genexpr>
    for ta, input_ in zip(input_ta, flatted_inputs))  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/util/tf_should_use.py", line 193, in wrapped
    return _add_should_use_warning(fn(*args, **kwargs))  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/ops/tensor_array_ops.py", line 1179, in unstack
    return self._implementation.unstack(value, name=name)  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/util/tf_should_use.py", line 193, in wrapped
    return _add_should_use_warning(fn(*args, **kwargs))
==================================
ERROR:tensorflow:==================================
Object was never used (type <class 'tensorflow.python.ops.tensor_array_ops.TensorArray'>):
<tensorflow.python.ops.tensor_array_ops.TensorArray object at 0x7fe56dbfdd68>
If you want to mark it as used call its "mark_used()" method.
It was originally created here:
  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/keras/backend.py", line 3443, in <genexpr>
    for ta, input_ in zip(input_ta, flatted_inputs))  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/util/tf_should_use.py", line 193, in wrapped
    return _add_should_use_warning(fn(*args, **kwargs))  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/ops/tensor_array_ops.py", line 1179, in unstack
    return self._implementation.unstack(value, name=name)  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/util/tf_should_use.py", line 193, in wrapped
    return _add_should_use_warning(fn(*args, **kwargs))  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/ops/tensor_array_ops.py", line 334, in unstack
    indices=math_ops.range(0, num_elements), value=value, name=name)  File "/home/zhuhang/Software/anaconda3/envs/py36tensor1/lib/python3.6/site-packages/tensorflow/python/util/tf_should_use.py", line 193, in wrapped
    return _add_should_use_warning(fn(*args, **kwargs))
Liyue-Chen commented 2 years ago

Thanks for your issues. We have fixed this bug about stacking multiple spatiotemporal layers (e.g., GRU or LSTM).

Star-live commented 2 years ago

Thank you very much! With your help, the issue was resolved.