Does anyone know why FID50k metric errors out?
When I set my --metrics=None, everything works fine(the network trains and generates pkls and images), but when I default to FID50k, I get this:
Traceback (most recent call last): File "run_training.py", line 223, in <module> main() File "run_training.py", line 218, in main run(**vars(args)) File "run_training.py", line 140, in run dnnlib.submit_run(**kwargs) File "./dnnlib/submission/submit.py", line 343, in submit_run return farm.submit(submit_config, host_run_dir) File "./dnnlib/submission/internal/local.py", line 22, in submit return run_wrapper(submit_config) File "./dnnlib/submission/submit.py", line 280, in run_wrapper run_func_obj(**submit_config.run_func_kwargs) File "./training/training_loop.py", line 377, in training_loop metrics.run(pkl, run_dir=dnnlib.make_run_dir_path(), data_dir=dnnlib.convert_path(data_dir), num_gpus=num_gpus, tf_config=tf_config) File "./metrics/metric_base.py", line 151, in run metric.run(*args, **kwargs) File "./metrics/metric_base.py", line 62, in run self._reset(network_pkl=network_pkl, run_dir=run_dir, data_dir=data_dir, dataset_args=dataset_args, mirror_augment=mirror_augment) File "./metrics/metric_base.py", line 39, in _reset self._dataset_obj.close() AttributeError: 'TFRecordDataset' object has no attribute 'close'
Hi there,
Does anyone know why FID50k metric errors out? When I set my --metrics=None, everything works fine(the network trains and generates pkls and images), but when I default to FID50k, I get this:
Traceback (most recent call last): File "run_training.py", line 223, in <module> main() File "run_training.py", line 218, in main run(**vars(args)) File "run_training.py", line 140, in run dnnlib.submit_run(**kwargs) File "./dnnlib/submission/submit.py", line 343, in submit_run return farm.submit(submit_config, host_run_dir) File "./dnnlib/submission/internal/local.py", line 22, in submit return run_wrapper(submit_config) File "./dnnlib/submission/submit.py", line 280, in run_wrapper run_func_obj(**submit_config.run_func_kwargs) File "./training/training_loop.py", line 377, in training_loop metrics.run(pkl, run_dir=dnnlib.make_run_dir_path(), data_dir=dnnlib.convert_path(data_dir), num_gpus=num_gpus, tf_config=tf_config) File "./metrics/metric_base.py", line 151, in run metric.run(*args, **kwargs) File "./metrics/metric_base.py", line 62, in run self._reset(network_pkl=network_pkl, run_dir=run_dir, data_dir=data_dir, dataset_args=dataset_args, mirror_augment=mirror_augment) File "./metrics/metric_base.py", line 39, in _reset self._dataset_obj.close() AttributeError: 'TFRecordDataset' object has no attribute 'close'
Any pointers?
Thanks in advance.