cant Train the model

[farshidrayhancv]

i used the following code in the terminal python train.py 0 And I got the following errors

Traceback (most recent call last):' File "train.py", line 240, in with tf.device(gpuNow):'

`File "/home/farshid/anaconda3/lib/python3.5/contextlib.py", line 59, in enter return next(self.gen)'

File "/home/farshid/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 3045, in device' device_function = pydev.merge_device(device_name_or_function)'

File "/home/farshid/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/device.py", line 282, in merge_device' spec = DeviceSpec.from_string(spec or "")'

File "/home/farshid/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/device.py", line 228, in from_string' return DeviceSpec().parse_from_string(spec)'

`File "/home/farshid/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/device.py", line 146, in parse_from_string'

splits = [x.split(":") for x in spec.split("/")]'AttributeError: 'int' object has no attribute 'split' `

[nzurita]

Do you have a GPU or just a CPU? Another thing I noted is you are using python 3.5, while train.py is ready for python 2, the only issue I think is with print function, if you use python 3 it must have parenthesis: print('Training Begin') instead of print 'Training Begin'.

If you have a CPU and not GPU try changing line 240 from with tf.device(gpuNow): to:

with tf.device("/cpu:0"):

[farshidrayhancv]

​OK. thanks

I will update you if it works or not ​

[image: Mailtrack] https://mailtrack.io?utm_source=gmail&utm_medium=signature&utm_campaign=signaturevirality3& Sender notified by Mailtrack https://mailtrack.io?utm_source=gmail&utm_medium=signature&utm_campaign=signaturevirality3&

Regards,

On Fri, Apr 20, 2018 at 1:09 PM, Norberto Zurita [email protected] wrote:

Do you have a GPU or just a CPU? Another thing I noted is you are using python 3.5, while train.py is ready for python 2, the only issue I think is with print function, if you use python 3 it must have parenthesis: print('Training Begin') instead of print 'Training Begin'.

If you have a CPU and not GPU try changing line 240 from with tf.device(gpuNow): to:

with tf.device("/cpu:0"):

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/huangshiyu13/RPNplus/issues/16#issuecomment-383002974, or mute the thread https://github.com/notifications/unsubscribe-auth/Ae9uRZhRCpd-PgI6908aUdx2luRTABNOks5tqYnFgaJpZM4Rur6A .