tensorflow tf.while_loop segmentation error when parallel_iterations=0 -
i'm wondering why tf.while_loop gives segmentation error when run below code while setting parallel_iterations=0, works fine long >0. there reason ?
import tensorflow tf import numpy np = tf.constant(0) s = tf.constant(0) x = tf.random_uniform([], 0, 761-64, dtype=tf.int32) p = tf.print(x, [x], message="this random x: ") # rand = tf.random c = lambda i,s,x,p: tf.less(i, 50) b = lambda i,s,x,p: (tf.add(i, 1), tf.add(s, x),tf.random_uniform([], 0, 761-64, dtype=tf.int32),tf.print(x, [x], message="this random x: ")) r = tf.while_loop(c, b, [i,s,x,p], parallel_iterations=1) sess = tf.session() init = tf.initialize_all_variables().run print sess.run(r)
the error looks follows: tensorflow/stream_executor/dso_loader.cc:108] opened cuda library libcublas.so locally tensorflow/stream_executor/dso_loader.cc:108] opened cuda library libcudnn.so.4 locally tensorflow/stream_executor/dso_loader.cc:108] opened cuda library libcufft.so locally tensorflow/stream_executor/dso_loader.cc:108] opened cuda library libcuda.so.1 locally tensorflow/stream_executor/dso_loader.cc:108] opened cuda library libcurand.so locally tensorflow/core/common_runtime/gpu/gpu_init.cc:102] found device 0 properties: name: geforce gtx titan x major: 5 minor: 2 memoryclockrate (ghz) 1.076 pcibusid 0000:04:00.0 total memory: 11.92gib free memory: 11.81gib tensorflow/core/common_runtime/gpu/gpu_init.cc:126] dma: 0 tensorflow/core/common_runtime/gpu/gpu_init.cc:136] 0: y tensorflow/core/common_runtime/gpu/gpu_device.cc:806] creating tensorflow device (/gpu:0) -> (device: 0, name: geforce gtx titan x, pci bus id: 0000:04:00.0) segmentation fault (core dumped)
why segmentation fault occur ?
Comments
Post a Comment