fjxmlzn / DoppelGANger

[IMC 2020 (Best Paper Finalist)] Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
http://arxiv.org/abs/1909.13403
BSD 3-Clause Clear License
296 stars 75 forks source link

Error in summary.merge function #11

Closed AbbasiAYE closed 3 years ago

AbbasiAYE commented 3 years ago

Hi Zinan Lin

I've been trying to run this on TF2 for a bit now, after chaning many lines from TF1 to TF2. I reached this point... any help is appreciated...

Traceback (most recent call last): File "/opt/conda/bin/start_gpu_task", line 11, in load_entry_point('GPUTaskScheduler', 'console_scripts', 'start_gpu_task')() File "/home/jovyan/GAN2/DoppelGANger/GPUTaskScheduler/gpu_task_scheduler/start_gpu_task.py", line 23, in main worker.main() File "/home/jovyan/GAN2/DoppelGANger/example_training/gan_task.py", line 120, in main gan.build() File "../gan/doppelganger.py", line 213, in build self.build_summary() File "../gan/doppelganger.py", line 516, in build_summary self.g_summary = tf.compat.v1.summary.merge(self.g_summary) File "/opt/conda/lib/python3.7/site-packages/tensorflow/python/summary/summary.py", line 371, in merge val = _gen_logging_ops.merge_summary(inputs=inputs, name=name) File "/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/gen_logging_ops.py", line 468, in merge_summary "MergeSummary", inputs=inputs, name=name) File "/opt/conda/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py", line 436, in _apply_op_helper (prefix, dtype.name))TypeError: Tensors in list passed to 'inputs' of 'MergeSummary' Op have types [bool, bool, bool] that do not match expected type string.

fjxmlzn commented 3 years ago

The code was developed on TF1. Running it with TF2 requires many changes. I do not know what changes you have made so it is hard for me the make sense of this error. Would you mind providing all the codes you modified?

Thanks!

AbbasiAYE commented 3 years ago

Its ok, thanks, issue solved.

Just a question out of curiosity, how long does the simulation run? how many GPUs do you usually use?

Thanks

fjxmlzn commented 3 years ago

Great!

For each experiment (one combination of the hyper-parameters), it takes less than ~72 hours to finish on 1 NVIDIA Tesla P100 GPU.