New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

CNN architechure search run error on tensorflow1.13 #111

Open

pingguokiller opened this issue Nov 12, 2019 · 0 comments

pingguokiller commented Nov 12, 2019

MemoryError
ERROR:tensorflow:==================================
Object was never used (type <class 'tensorflow.python.framework.ops.Tensor'>):
<tf.Tensor 'report_uninitialized_variables/boolean_mask/GatherV2:0' shape=(?,) dtype=string>
If you want to mark it as used call its "mark_used()" method.
It was originally created here:
File "main.py", line 338, in
tf.app.run() File "/home/zjw/anaconda3/envs/tf113/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv)) File "main.py", line 334, in main
train() File "main.py", line 311, in train
break File "main.py", line 199, in get_ops
return ops File "/home/zjw/code/research/enas/enascifar/general_controller.py", line 277, in build_trainer
num_replicas=self.num_replicas) File "/home/zjw/code/research/enas/utils.py", line 224, in get_train_ops
return train_op, learning_rate, grad_norm, opt File "/home/zjw/anaconda3/envs/tf113/lib/python3.6/site-packages/tensorflow/python/training/sync_replicas_optimizer.py", line 360, in apply_gradients
return train_op File "/home/zjw/anaconda3/envs/tf113/lib/python3.6/site-packages/tensorflow/python/util/tf_should_use.py", line 193, in wrapped
return _add_should_use_warning(fn(*args, **kwargs))

Did somebody solve this problem>

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment