InternalError (see above for traceback): Blas GEMM launch failed : a.shape=(x, x), b.shape=(x,x)錯誤

前言

這個錯誤是在一開始訓練Keras（使用TensorFlow當backend）模型的時候就出現。
Python版本：3.5.2
Keras版本：2.1.2
TensorFlow版本：1.3.0

錯誤訊息

InternalErrorTraceback (most recent call last)
/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1326 try:
-> 1327 return fn(*args)
1328 except errors.OpError as e:
/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
1305 feed_dict, fetch_list, target_list,
-> 1306 status, run_metadata)
1307
/usr/lib/python3.5/contextlib.py in exit(self, type, value, traceback)
65 try:
—> 66 next(self.gen)
67 except StopIteration:
/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/errors_impl.py in raise_exception_on_not_ok_status()
465 compat.as_text(pywrap_tensorflow.TF_Message(status)),
–> 466 pywrap_tensorflow.TF_GetCode(status))
467 finally:
InternalError: Blas GEMM launch failed : a.shape=(10, 512), b.shape=(512, 512), m=10, n=512, k=512
[[Node: lstm_1/while/MatMul_4 = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/gpu:0"](lstm_1/while/Identity_2, lstm_1/while/MatMul_4/Enter)]]
[[Node: loss/mul/_97 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name=“edge_1992_loss/mul”, tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]]
During handling of the above exception, another exception occurred:
InternalErrorTraceback (most recent call last)
in ()
10 model.compile(loss=‘mse’, optimizer=‘adam’)
11 # fit network
—> 12 history = model.fit(X_train, y_train, epochs=3000, batch_size=16, validation_data=(x_test, y_test), verbose=2, shuffle=False)
13 #history = model.fit(X,y, epochs=3000, batch_size=16, verbose=2, shuffle=False)
14 # plot history
/usr/local/lib/python3.5/dist-packages/keras/models.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, **kwargs)
958 initial_epoch=initial_epoch,
959 steps_per_epoch=steps_per_epoch,
–> 960 validation_steps=validation_steps)
961
962 def evaluate(self, x, y, batch_size=32, verbose=1,
/usr/local/lib/python3.5/dist-packages/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, **kwargs)
1655 initial_epoch=initial_epoch,
1656 steps_per_epoch=steps_per_epoch,
-> 1657 validation_steps=validation_steps)
1658
1659 def evaluate(self, x=None, y=None,
/usr/local/lib/python3.5/dist-packages/keras/engine/training.py in _fit_loop(self, f, ins, out_labels, batch_size, epochs, verbose, callbacks, val_f, val_ins, shuffle, callback_metrics, initial_epoch, steps_per_epoch, validation_steps)
1211 batch_logs[‘size’] = len(batch_ids)
1212 callbacks.on_batch_begin(batch_index, batch_logs)
-> 1213 outs = f(ins_batch)
1214 if not isinstance(outs, list):
1215 outs = [outs]
/usr/local/lib/python3.5/dist-packages/keras/backend/tensorflow_backend.py in call(self, inputs)
2355 session = get_session()
2356 updated = session.run(fetches=fetches, feed_dict=feed_dict,
-> 2357 **self.session_kwargs)
2358 return updated[:len(self.outputs)]
2359
/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
893 try:
894 result = self._run(None, fetches, feed_dict, options_ptr,
–> 895 run_metadata_ptr)
896 if run_metadata:
897 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
1122 if final_fetches or final_targets or (handle and feed_dict_tensor):
1123 results = self._do_run(handle, final_targets, final_fetches,
-> 1124 feed_dict_tensor, options, run_metadata)
1125 else:
1126 results = []
/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1319 if handle is None:
1320 return self._do_call(_run_fn, self._session, feeds, fetches, targets,
-> 1321 options, run_metadata)
1322 else:
1323 return self._do_call(_prun_fn, self._session, handle, feeds, fetches)
/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1338 except KeyError:
1339 pass
-> 1340 raise type(e)(node_def, op, message)
1341
1342 def _extend_graph(self):
InternalError: Blas GEMM launch failed : a.shape=(10, 512), b.shape=(512, 512), m=10, n=512, k=512
[[Node: lstm_1/while/MatMul_4 = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/gpu:0"](lstm_1/while/Identity_2, lstm_1/while/MatMul_4/Enter)]]
[[Node: loss/mul/_97 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name=“edge_1992_loss/mul”, tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]]
Caused by op ‘lstm_1/while/MatMul_4’, defined at:
File “/usr/lib/python3.5/runpy.py”, line 184, in _run_module_as_main
“main”, mod_spec)
File “/usr/lib/python3.5/runpy.py”, line 85, in _run_code
exec(code, run_globals)
File “/usr/local/lib/python3.5/dist-packages/ipykernel_launcher.py”, line 16, in
app.launch_new_instance()
File “/usr/local/lib/python3.5/dist-packages/traitlets/config/application.py”, line 658, in launch_instance
app.start()
File “/usr/local/lib/python3.5/dist-packages/ipykernel/kernelapp.py”, line 477, in start
ioloop.IOLoop.instance().start()
File “/usr/local/lib/python3.5/dist-packages/zmq/eventloop/ioloop.py”, line 177, in start
super(ZMQIOLoop, self).start()
File “/usr/local/lib/python3.5/dist-packages/tornado/ioloop.py”, line 888, in start
handler_func(fd_obj, events)
File “/usr/local/lib/python3.5/dist-packages/tornado/stack_context.py”, line 277, in null_wrapper
return fn(*args, **kwargs)
File “/usr/local/lib/python3.5/dist-packages/zmq/eventloop/zmqstream.py”, line 440, in _handle_events
self._handle_recv()
File “/usr/local/lib/python3.5/dist-packages/zmq/eventloop/zmqstream.py”, line 472, in _handle_recv
self._run_callback(callback, msg)
File “/usr/local/lib/python3.5/dist-packages/zmq/eventloop/zmqstream.py”, line 414, in _run_callback
callback(*args, **kwargs)
File “/usr/local/lib/python3.5/dist-packages/tornado/stack_context.py”, line 277, in null_wrapper
return fn(*args, **kwargs)
File “/usr/local/lib/python3.5/dist-packages/ipykernel/kernelbase.py”, line 283, in dispatcher
return self.dispatch_shell(stream, msg)
File “/usr/local/lib/python3.5/dist-packages/ipykernel/kernelbase.py”, line 235, in dispatch_shell
handler(stream, idents, msg)
File “/usr/local/lib/python3.5/dist-packages/ipykernel/kernelbase.py”, line 399, in execute_request
user_expressions, allow_stdin)
File “/usr/local/lib/python3.5/dist-packages/ipykernel/ipkernel.py”, line 196, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File “/usr/local/lib/python3.5/dist-packages/ipykernel/zmqshell.py”, line 533, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File “/usr/local/lib/python3.5/dist-packages/IPython/core/interactiveshell.py”, line 2698, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File “/usr/local/lib/python3.5/dist-packages/IPython/core/interactiveshell.py”, line 2802, in run_ast_nodes
if self.run_code(code, result):
File “/usr/local/lib/python3.5/dist-packages/IPython/core/interactiveshell.py”, line 2862, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File “”, line 7, in
model.add(LSTM(512, input_shape=(X.shape[1], X.shape[2])))
File “/usr/local/lib/python3.5/dist-packages/keras/models.py”, line 464, in add
layer(x)
File “/usr/local/lib/python3.5/dist-packages/keras/layers/recurrent.py”, line 482, in call
return super(RNN, self).call(inputs, **kwargs)
File “/usr/local/lib/python3.5/dist-packages/keras/engine/topology.py”, line 603, in call
output = self.call(inputs, **kwargs)
File “/usr/local/lib/python3.5/dist-packages/keras/layers/recurrent.py”, line 2023, in call
initial_state=initial_state)
File “/usr/local/lib/python3.5/dist-packages/keras/layers/recurrent.py”, line 589, in call
input_length=timesteps)
File “/usr/local/lib/python3.5/dist-packages/keras/backend/tensorflow_backend.py”, line 2646, in rnn
swap_memory=True)
File “/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/control_flow_ops.py”, line 2775, in while_loop
result = context.BuildLoop(cond, body, loop_vars, shape_invariants)
File “/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/control_flow_ops.py”, line 2604, in BuildLoop
pred, body, original_loop_vars, loop_vars, shape_invariants)
File “/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/control_flow_ops.py”, line 2554, in _BuildLoop
body_result = body(*packed_vars_for_body)
File “/usr/local/lib/python3.5/dist-packages/keras/backend/tensorflow_backend.py”, line 2632, in _step
tuple(constants))
File “/usr/local/lib/python3.5/dist-packages/keras/layers/recurrent.py”, line 580, in step
return self.cell.call(inputs, states, **kwargs)
File “/usr/local/lib/python3.5/dist-packages/keras/layers/recurrent.py”, line 1836, in call
self.recurrent_kernel_i))
File “/usr/local/lib/python3.5/dist-packages/keras/backend/tensorflow_backend.py”, line 1057, in dot
out = tf.matmul(x, y)
File “/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/math_ops.py”, line 1844, in matmul
a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
File “/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/gen_math_ops.py”, line 1289, in _mat_mul
transpose_b=transpose_b, name=name)
File “/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py”, line 767, in apply_op
op_def=op_def)
File “/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py”, line 2630, in create_op
original_op=self._default_original_op, op_def=op_def)
File “/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py”, line 1204, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InternalError (see above for traceback): Blas GEMM launch failed : a.shape=(10, 512), b.shape=(512, 512), m=10, n=512, k=512
[[Node: lstm_1/while/MatMul_4 = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/gpu:0"](lstm_1/while/Identity_2, lstm_1/while/MatMul_4/Enter)]]
[[Node: loss/mul/_97 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name=“edge_1992_loss/mul”, tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]]

解決辦法

使用nvidia-smi查看GPU memory的使用情況：

發現己被其它程序佔滿。
試著將這些程序關掉，然後再重新運行剛剛那段代碼（不必重啟kernel），問題即可成功解決！