Open lemonsee opened 7 years ago
I have a machine that have 16 CPUs ,but only one cpu is running (100% full load) when I execute " python eval.py",why?
I have set the config.py like this :
session_conf = tf.ConfigProto( device_count={'CPU':8}, intra_op_parallelism_threads=4, log_device_placement=False )
here is some information about devices :
print(device_lib.list_local_devices()) [name: "/cpu:0" device_type: "CPU" memory_limit: 268435456 locality { } incarnation: 12312707312159520189 ]
I hope that all CPUs in my machine can be used to speed up the evaluation . I need help , thx !!!
@lemonsee hmm.. I'm not sure but this could be the answer.. https://stackoverflow.com/questions/38836269/does-tensorflow-view-all-cpus-of-one-machine-as-one-device
I have a machine that have 16 CPUs ,but only one cpu is running (100% full load) when I execute " python eval.py",why?
I have set the config.py like this :
here is some information about devices :
I hope that all CPUs in my machine can be used to speed up the evaluation . I need help , thx !!!