Question

我正在尝试使用笔记本电脑的gpu使用tensorflow对模拟数据集（代码部分＃1 ）执行线性回归（代码部分＃2 ）。我的问题在于，根据成本函数块中y_pred的定义方式，我在gpu上运行该块时得到InternalError。然而在cpu上运行它很好。回溯显示在此问题的末尾（ Traceback ）。

所以问题是：这个内部错误的原因是什么？我该如何解决这个问题，以便我可以使用tf.matmul？

规格：笔记本电脑运行的是Windows 10 64bit，并配有GeForce 940MX卡和Intel HD图形630.在软件方面，笔记本电脑正在运行cuda 9.0和相应的cudnn。

代码＃1 ：

import matplotlib.pylab as plt
import tensorflow as tf
import numpy as np

# generate some linear train and test data
X_train = np.linspace(0,1,100).reshape((-1,1))
t_train = X_train.dot([1])
t_train = t_train.reshape((-1,1))

X_test = np.linspace(0,1,150).reshape((-1,1))
t_test = X_test.dot([1])
t_tets = t_test.reshape((-1,1))

N, D = X_train.shape

fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(X_train, t_train, '.', label="train")
ax.plot(X_test, t_test, '.', label="test")
plt.legend()
plt.show()

代码＃2 ：

tf.reset_default_graph()

cpu = "/cpu:0"
gpu = "/gpu:0"

# placeholders and weights variable
with tf.device(cpu):
    X = tf.placeholder(tf.float32, shape=(None,D), name="X")
    y = tf.placeholder(tf.float32, shape=(None,1), name="y")
    w = tf.Variable(tf.ones([D,1])*10, name="w")

    learning_rate = .1

# cost function
with tf.device(gpu):
    y_pred = tf.matmul(X,w) # does not work
    #y_pred = X*w # works
    error = y_pred - y
    cost = tf.reduce_mean(tf.square(error))

# update rule
with tf.device(cpu):
    gradient = tf.gradients(cost, [w])[0] 
    update = tf.assign(w, w - learning_rate * gradient)

init = tf.global_variables_initializer()

n_epochs = 500
n_print = 50

with tf.Session() as sess:

    sess.run(init)

    for epoch in range(n_epochs):

        sess.run(update, feed_dict={X:X_train, y:t_train})

        if epoch % n_print == 0:
            print("epoch",epoch,
                  ": cost",cost.eval(feed_dict={X:X_train, y:t_train}),
                  "w",w.eval())

代码＃2中由tf.matmul引起的

回溯：

---------------------------------------------------------------------------
InternalError                             Traceback (most recent call last)
E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\tensorflow\python\client\session.py in _do_call(self, fn, *args)
   1360     try:
-> 1361       return fn(*args)
   1362     except errors.OpError as e:

E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\tensorflow\python\client\session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
   1339           return tf_session.TF_Run(session, options, feed_dict, fetch_list,
-> 1340                                    target_list, status, run_metadata)
   1341 

E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\tensorflow\python\framework\errors_impl.py in __exit__(self, type_arg, value_arg, traceback_arg)
    515             compat.as_text(c_api.TF_Message(self.status.status)),
--> 516             c_api.TF_GetCode(self.status.status))
    517     # Delete the underlying status object from memory otherwise it stays alive

InternalError: Blas GEMV launch failed:  m=1, n=100
     [[Node: MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](_arg_X_0_0/_1, w/read/_3)]]
     [[Node: sub/_11 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_21_sub", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

During handling of the above exception, another exception occurred:

InternalError                             Traceback (most recent call last)
<ipython-input-4-0375a84ed72a> in <module>()
     11     for epoch in range(n_epochs):
     12 
---> 13         sess.run(update, feed_dict={X:X_train, y:t_train})
     14 
     15         if epoch % n_print == 0:

E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\tensorflow\python\client\session.py in run(self, fetches, feed_dict, options, run_metadata)
    903     try:
    904       result = self._run(None, fetches, feed_dict, options_ptr,
--> 905                          run_metadata_ptr)
    906       if run_metadata:
    907         proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\tensorflow\python\client\session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
   1135     if final_fetches or final_targets or (handle and feed_dict_tensor):
   1136       results = self._do_run(handle, final_targets, final_fetches,
-> 1137                              feed_dict_tensor, options, run_metadata)
   1138     else:
   1139       results = []

E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\tensorflow\python\client\session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
   1353     if handle is None:
   1354       return self._do_call(_run_fn, self._session, feeds, fetches, targets,
-> 1355                            options, run_metadata)
   1356     else:
   1357       return self._do_call(_prun_fn, self._session, handle, feeds, fetches)

E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\tensorflow\python\client\session.py in _do_call(self, fn, *args)
   1372         except KeyError:
   1373           pass
-> 1374       raise type(e)(node_def, op, message)
   1375 
   1376   def _extend_graph(self):

InternalError: Blas GEMV launch failed:  m=1, n=100
     [[Node: MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](_arg_X_0_0/_1, w/read/_3)]]
     [[Node: sub/_11 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_21_sub", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

Caused by op 'MatMul', defined at:
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\ipykernel\__main__.py", line 3, in <module>
    app.launch_new_instance()
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\traitlets\config\application.py", line 658, in launch_instance
    app.start()
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\ipykernel\kernelapp.py", line 477, in start
    ioloop.IOLoop.instance().start()
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\zmq\eventloop\ioloop.py", line 177, in start
    super(ZMQIOLoop, self).start()
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\tornado\ioloop.py", line 888, in start
    handler_func(fd_obj, events)
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\zmq\eventloop\zmqstream.py", line 440, in _handle_events
    self._handle_recv()
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\zmq\eventloop\zmqstream.py", line 472, in _handle_recv
    self._run_callback(callback, msg)
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\zmq\eventloop\zmqstream.py", line 414, in _run_callback
    callback(*args, **kwargs)
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\ipykernel\kernelbase.py", line 283, in dispatcher
    return self.dispatch_shell(stream, msg)
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\ipykernel\kernelbase.py", line 235, in dispatch_shell
    handler(stream, idents, msg)
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\ipykernel\kernelbase.py", line 399, in execute_request
    user_expressions, allow_stdin)
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\ipykernel\ipkernel.py", line 196, in do_execute
    res = shell.run_cell(code, store_history=store_history, silent=silent)
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\ipykernel\zmqshell.py", line 533, in run_cell
    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\IPython\core\interactiveshell.py", line 2717, in run_cell
    interactivity=interactivity, compiler=compiler, result=result)
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\IPython\core\interactiveshell.py", line 2821, in run_ast_nodes
    if self.run_code(code, result):
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\IPython\core\interactiveshell.py", line 2881, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-3-9dfe23bd6608>", line 16, in <module>
    y_pred = tf.matmul(X,w) # does not work
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\tensorflow\python\ops\math_ops.py", line 2064, in matmul
    a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\tensorflow\python\ops\gen_math_ops.py", line 2790, in _mat_mul
    name=name)
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\tensorflow\python\framework\ops.py", line 3271, in create_op
    op_def=op_def)
  File "E:\Programs\Anaconda3\envs\py35-gpu\lib\site-packages\tensorflow\python\framework\ops.py", line 1650, in __init__
    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

InternalError (see above for traceback): Blas GEMV launch failed:  m=1, n=100
     [[Node: MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](_arg_X_0_0/_1, w/read/_3)]]
     [[Node: sub/_11 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_21_sub", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

tf.matmul在gpu-enabled tensorflow和＆＃39; InternalError：Blas GEMV启动失败＆＃39;

0 个答案: