TensorFlow: InternalError: Blas SGEMM launch failed
When I run sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys}) I get InternalError: Blas SGEMM launch failed. Here is the full error and stack trace:
InternalErrorTraceback (most recent call last)
<ipython-input-9-a3261a02bdce> in <module>()
1 batch_xs, batch_ys = mnist.train.next_batch(100)
----> 2 sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.pyc in run(self, fetches, feed_dict, options, run_metadata)
338 try:
339 result = self._run(None, fetches, feed_dict, options_ptr,
--> 340 run_metadata_ptr)
341 if run_metadata:
342 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.pyc in _run(self, handle, fetches, feed_dict, options, run_metadata)
562 try:
563 results = self._do_run(handle, target_list, unique_fetches,
--> 564 feed_dict_string, options, run_metadata)
565 finally:
566 # The movers are no longer used. Delete them.
/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.pyc in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
635 if handle is None:
636 return self._do_call(_run_fn, self._session, feed_dict, fetch_list,
--> 637 target_list, options, run_metadata)
638 else:
639 return self._do_call(_prun_fn, self._session, handle, feed_dict,
/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.pyc in _do_call(self, fn, *args)
657 # pylint: disable=protected-access
658 raise errors._make_specific_exception(node_def, op, error_message,
--> 659 e.code)
660 # pylint: enable=protected-access
661
InternalError: Blas SGEMM launch failed : a.shape=(100, 784), b.shape=(784, 10), m=100, n=10, k=784
[[Node: MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/gpu:0"](_recv_Placeholder_0/_4, Variable/read)]]
Caused by op u'MatMul', defined at:
File "/usr/lib/python2.7/runpy.py", line 162, in _run_module_as_main
"__main__", fname, loader, pkg_name)
File "/usr/lib/python2.7/runpy.py", line 72, in _run_code
exec code in run_globals
File "/usr/local/lib/python2.7/dist-packages/ipykernel/__main__.py", line 3, in <module>
app.launch_new_instance()
File "/usr/local/lib/python2.7/dist-packages/traitlets/config/application.py", line 596, in launch_instance
app.start()
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelapp.py", line 442, in start
ioloop.IOLoop.instance().start()
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/ioloop.py", line 162, in start
super(ZMQIOLoop, self).start()
File "/usr/local/lib/python2.7/dist-packages/tornado/ioloop.py", line 883, in start
handler_func(fd_obj, events)
File "/usr/local/lib/python2.7/dist-packages/tornado/stack_context.py", line 275, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events
self._handle_recv()
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/tornado/stack_context.py", line 275, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelbase.py", line 276, in dispatcher
return self.dispatch_shell(stream, msg)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelbase.py", line 228, in dispatch_shell
handler(stream, idents, msg)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelbase.py", line 391, in execute_request
user_expressions, allow_stdin)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/ipkernel.py", line 199, in do_execute
shell.run_cell(code, store_history=store_history, silent=silent)
File "/usr/local/lib/python2.7/dist-packages/IPython/core/interactiveshell.py", line 2723, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/usr/local/lib/python2.7/dist-packages/IPython/core/interactiveshell.py", line 2825, in run_ast_nodes
if self.run_code(code, result):
File "/usr/local/lib/python2.7/dist-packages/IPython/core/interactiveshell.py", line 2885, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-4-d7414c4b6213>", line 4, in <module>
y = tf.nn.softmax(tf.matmul(x, W) + b)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_ops.py", line 1036, in matmul
name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_math_ops.py", line 911, in _mat_mul
transpose_b=transpose_b, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/op_def_library.py", line 655, in apply_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2154, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1154, in __init__
self._traceback = _extract_stack()
Stack: EC2 g2.8xlarge machine, Ubuntu 14.04
Solution 1:
Old question, but may help others.
Try to close interactive sessions active in other processes (if IPython Notebook - just restart kernels). This helped me!
Additionally, I use this code to close local sessions in this kernel during experiments:
if 'session' in locals() and session is not None:
print('Close interactive session')
session.close()
Solution 2:
I encountered this problem and solved it by setting allow_soft_placement=True and gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.3), which specifically define the fraction of memory of GPU been used. I guess this has helped to avoid two tensorflow processes competing for the GPU memory.
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.3)
sess = tf.Session(config=tf.ConfigProto(
allow_soft_placement=True, log_device_placement=True))
Solution 3:
I got this error when running Tensorflow Distributed. Did you check if any of the workers were reporting CUDA_OUT_OF_MEMORY errors? If this is the case it may have to do with where you place your weight and bias variables. E.g.
with tf.device("/job:paramserver/task:0/cpu:0"):
W = weight_variable([input_units, num_hidden_units])
b = bias_variable([num_hidden_units])
Solution 4:
My environment is Python 3.5, Tensorflow 0.12 and Windows 10 (no Docker). I am training neural networks in both CPU and GPU. I came across the same error InternalError: Blas SGEMM launch failed whenever training in the GPU.
I could not find the reason why this error happens but I managed to run my code in the GPU by avoiding the tensorflow function tensorflow.contrib.slim.one_hot_encoding(). Instead, I do the one-hot-encoding operation in numpy (input and output variables).
The following code reproduces the error and the fix. It is a minimal setup to learn the y = x ** 2 function using gradient descent.
import numpy as np
import tensorflow as tf
import tensorflow.contrib.slim as slim
def test_one_hot_encoding_using_tf():
# This function raises the "InternalError: Blas SGEMM launch failed" when run in the GPU
# Initialize
tf.reset_default_graph()
input_size = 10
output_size = 100
input_holder = tf.placeholder(shape=[1], dtype=tf.int32, name='input')
output_holder = tf.placeholder(shape=[1], dtype=tf.int32, name='output')
# Define network
input_oh = slim.one_hot_encoding(input_holder, input_size)
output_oh = slim.one_hot_encoding(output_holder, output_size)
W1 = tf.Variable(tf.random_uniform([input_size, output_size], 0, 0.01))
output_v = tf.matmul(input_oh, W1)
output_v = tf.reshape(output_v, [-1])
# Define updates
loss = tf.reduce_sum(tf.square(output_oh - output_v))
trainer = tf.train.GradientDescentOptimizer(learning_rate=0.1)
update_model = trainer.minimize(loss)
# Optimize
init = tf.initialize_all_variables()
steps = 1000
# Force CPU/GPU
config = tf.ConfigProto(
# device_count={'GPU': 0} # uncomment this line to force CPU
)
# Launch the tensorflow graph
with tf.Session(config=config) as sess:
sess.run(init)
for step_i in range(steps):
# Get sample
x = np.random.randint(0, 10)
y = np.power(x, 2).astype('int32')
# Update
_, l = sess.run([update_model, loss], feed_dict={input_holder: [x], output_holder: [y]})
# Check model
print('Final loss: %f' % l)
def test_one_hot_encoding_no_tf():
# This function does not raise the "InternalError: Blas SGEMM launch failed" when run in the GPU
def oh_encoding(label, num_classes):
return np.identity(num_classes)[label:label + 1].astype('int32')
# Initialize
tf.reset_default_graph()
input_size = 10
output_size = 100
input_holder = tf.placeholder(shape=[1, input_size], dtype=tf.float32, name='input')
output_holder = tf.placeholder(shape=[1, output_size], dtype=tf.float32, name='output')
# Define network
W1 = tf.Variable(tf.random_uniform([input_size, output_size], 0, 0.01))
output_v = tf.matmul(input_holder, W1)
output_v = tf.reshape(output_v, [-1])
# Define updates
loss = tf.reduce_sum(tf.square(output_holder - output_v))
trainer = tf.train.GradientDescentOptimizer(learning_rate=0.1)
update_model = trainer.minimize(loss)
# Optimize
init = tf.initialize_all_variables()
steps = 1000
# Force CPU/GPU
config = tf.ConfigProto(
# device_count={'GPU': 0} # uncomment this line to force CPU
)
# Launch the tensorflow graph
with tf.Session(config=config) as sess:
sess.run(init)
for step_i in range(steps):
# Get sample
x = np.random.randint(0, 10)
y = np.power(x, 2).astype('int32')
# One hot encoding
x = oh_encoding(x, 10)
y = oh_encoding(y, 100)
# Update
_, l = sess.run([update_model, loss], feed_dict={input_holder: x, output_holder: y})
# Check model
print('Final loss: %f' % l)