zsdonghao / Unsup-Im2Im

Unsupervised Image to Image Translation with Generative Adversarial Networks
https://github.com/zsdonghao/tensorlayer
73 stars 16 forks source link

What is the version of tensorflow? #10

Open zzw1123 opened 6 years ago

zzw1123 commented 6 years ago

Hi,donghao, I am running this project but I find there are so many errors at the beginning of my training, e.g. Traceback (most recent call last): File "train.py", line 362, in tf.app.run() File "/home/zzw/Program/anaconda2/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File "train.py", line 355, in main train_ac_gan() File "train.py", line 98, in train_ac_gan g_loss_fake = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(d_logits_fake, tf.ones_like(d_logits_fake))) File "/home/zzw/Program/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/nn_impl.py", line 149, in sigmoid_cross_entropy_with_logits labels, logits) File "/home/zzw/Program/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/nn_ops.py", line 1512, in _ensure_xent_args "named arguments (labels=..., logits=..., ...)" % name) ValueError: Only call sigmoid_cross_entropy_with_logits with named arguments (labels=..., logits=..., ...)

I guess these errors are due to differences between mine and yours,so could you please tell me what is your version of tensorflow?

zsdonghao commented 6 years ago

i think it is TF1.0+

zzw1123 commented 6 years ago

Okay,I changed some arguments' order then the errors disappeared. By the way,which conference is this paper contributed to?

zsdonghao commented 6 years ago

great. it is an arXiv paper