问题
I'm trying to get started with tensorflow using the python interface. My problem is that executing even the most basic operations, they take a long time (> 5 minutes)
This problem occurs when using python3.6, installed from macports and tensorflow-1.13, the tf-nightly, and tensorflow2.0 alpha, all installed using pip.
This simple example takes more than 5 minutes to execute.
> ipython
Python 3.6.8 (default, Dec 30 2018, 13:01:27)
In [1]: import numpy as np
In [2]: import tensorflow as tf
In [3]: print(tf.__version__)
1.13.1
In [4]: a = tf.constant(4.0, dtype=tf.float32)
After some time, I interrupted the execution, the traceback is below. Does anyone have a suggestion?
KeyboardInterrupt
Traceback (most recent call last) in
----> 1 a = tf.constant(4.0, dtype=tf.float32)
/opt/local/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in constant_v1(value, dtype, shape, name, verify_shape)
177 """
178 return _constant_impl(value, dtype, shape, name, verify_shape=verify_shape,
--> 179 allow_broadcast=False)
180
181
/opt/local/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in _constant_impl(value, dtype, shape, name, verify_shape, allow_broadcast)
287 attrs={"value": tensor_value,
288 "dtype": dtype_value},
--> 289 name=name).outputs[0]
290 return const_tensor
291
/opt/local/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py in new_func(*args, **kwargs)
505 'in a future version' if date is None else ('after %s' % date),
506 instructions)
--> 507 return func(*args, **kwargs)
508
509 doc = _add_deprecated_arg_notice_to_docstring(
/opt/local/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in create_op(failed resolving arguments)
3298 input_types=input_types,
3299 original_op=self._default_original_op,
-> 3300 op_def=op_def)
3301 self._create_op_helper(ret, compute_device=compute_device)
3302 return ret
/opt/local/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in init(self, node_def, g, inputs, output_types, control_inputs, input_types, original_op, op_def)
1821 op_def, inputs, node_def.attr)
1822 self._c_op = _create_c_op(self._graph, node_def, grouped_inputs,
-> 1823 control_input_ops)
1824
1825 # Initialize self._outputs.
/opt/local/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in _create_c_op(graph, node_def, inputs, control_inputs)
1654 # TODO(skyewm): this creates and deletes a new TF_Status for every attr.
1655 # It might be worth creating a convenient way to re-use the same status.
-> 1656 c_api.TF_SetAttrValueProto(op_desc, compat.as_str(name), serialized)
1657
1658 try:
KeyboardInterrupt:
来源：https://stackoverflow.com/questions/55335828/tensorflow-operations-are-unsusably-slow