Which verson of Tensorflow is required for CoGAN-tensorflow?

[kaihuchen]

Which verson of Tensorflow is required for CoGAN-tensorflow? I tried it on v0.12.1 and got the following error:

$ python main.py --is_train True --dataset mnist

I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcublas.so locally
I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcudnn.so locally
I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcufft.so locally
I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcurand.so locally
{'batch_size': 128,
 'beta1': 0.5,
 'c_dim': 3,
 'checkpoint_dir': 'checkpoint',
 'dataset': 'mnist',
 'epoch': 25,
 'is_crop': False,
 'is_train': True,
 'learning_rate': 0.0002,
 'output_size': 64,
 'sample_dir': 'samples',
 'train_size': inf,
 'visualize': False}
I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
I tensorflow/core/common_runtime/gpu/gpu_device.cc:885] Found device 0 with properties:
name: GRID K520
major: 3 minor: 0 memoryClockRate (GHz) 0.797
pciBusID 0000:00:03.0
Total memory: 3.94GiB
Free memory: 3.91GiB
I tensorflow/core/common_runtime/gpu/gpu_device.cc:906] DMA: 0
I tensorflow/core/common_runtime/gpu/gpu_device.cc:916] 0:   Y
I tensorflow/core/common_runtime/gpu/gpu_device.cc:975] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GRID K520, pci bus id: 0000:00:03.0)
WARNING:tensorflow:From /mnt/ml/tests/CoGAN-tensorflow/model.py:87 in build_model.: histogram_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30.
Instructions for updating:
Please switch to tf.summary.histogram. Note that tf.summary.histogram uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on their scope.
Traceback (most recent call last):
  File "main.py", line 51, in 
    tf.app.run()
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 43, in run
    sys.exit(main(sys.argv[:1] + flags_passthrough))
  File "main.py", line 41, in main
    dataset_name=FLAGS.dataset, is_crop=FLAGS.is_crop, checkpoint_dir=FLAGS.checkpoint_dir)
  File "/mnt/ml/tests/CoGAN-tensorflow/model.py", line 68, in __init__
    self.build_model()
  File "/mnt/ml/tests/CoGAN-tensorflow/model.py", line 96, in build_model
    self.G2 = self.generator(self.z, self.y, share_params=True, reuse=False, name='G2')
  File "/mnt/ml/tests/CoGAN-tensorflow/model.py", line 309, in generator
    h0 = prelu(self.g_bn0(linear(z, self.gfc_dim, 'g_h0_lin', reuse=share_params), reuse=share_params),
  File "/mnt/ml/tests/CoGAN-tensorflow/ops.py", line 37, in __call__
    ema_apply_op = self.ema.apply([batch_mean, batch_var])
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/moving_averages.py", line 391, in apply
    self._averages[var], var, decay, zero_debias=zero_debias))
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/moving_averages.py", line 70, in assign_moving_average
    update_delta = _zero_debias(variable, value, decay)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/moving_averages.py", line 177, in _zero_debias
    trainable=False)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 1024, in get_variable
    custom_getter=custom_getter)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 850, in get_variable
    custom_getter=custom_getter)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 346, in get_variable
    validate_shape=validate_shape)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 331, in _true_getter
    caching_device=caching_device, validate_shape=validate_shape)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 650, in _get_single_variable
    "VarScope?" % name)
ValueError: Variable g_bn0/g_bn0_2/g_bn0_2/moments_1/moments_1/mean/ExponentialMovingAverage/biased does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?

[andrewliao11]

I used tf.0.10 when i implement this project, and all work smoothly.
If you're using version later than tf.0.11, this tf bugs show up, see tensorflow/issue
I'm trying to fix it for version later than tf.0.11, thx!

[andrewliao11]

plz check it out the newest commit!
btw, your academic blogs looks quite nice 😄

[kaihuchen]

Thanks for the quick fix! It runs smoothly without the error now.

Glad that you enjoy my blog. If you have any input please feel free to let me know.