Training on CPU, facing error in code conversion

[navinthenapster]

I like to edit the code for CPU computation, but facing with error as given below. I tried to change the Trainer and config but got stuck. need help

Traceback (most recent call last): File "train1.py", line 86, in train(args, logdir=logdir_train1) File "train1.py", line 66, in train launch_train_with_config(train_conf, trainer ) File "/usr/local/lib/python2.7/dist-packages/tensorpack/train/interface.py", line 85, in launch_train_with_config model._build_graph_get_cost, model.get_optimizer) File "/usr/local/lib/python2.7/dist-packages/tensorpack/utils/argtools.py", line 181, in wrapper return func(*args, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorpack/train/tower.py", line 202, in setup_graph input_callbacks = self._setup_input(inputs_desc, input) File "/usr/local/lib/python2.7/dist-packages/tensorpack/train/tower.py", line 218, in _setup_input return input.setup(inputs_desc) File "/usr/local/lib/python2.7/dist-packages/tensorpack/utils/argtools.py", line 181, in wrapper return func(*args, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorpack/input_source/input_source_base.py", line 99, in setup return self.get_callbacks() File "/usr/local/lib/python2.7/dist-packages/functools32/functools32.py", line 378, in wrapper result = user_function(*args, **kwds) File "/usr/local/lib/python2.7/dist-packages/tensorpack/input_source/input_source_base.py", line 126, in get_callbacks before_train=lambda _: self.reset_state())] + self._get_callbacks() File "/usr/local/lib/python2.7/dist-packages/tensorpack/input_source/input_source.py", line 245, in _get_callbacks return [cb, self._create_ema_callback(), _get_reset_callback(self._inf_ds)] File "/usr/local/lib/python2.7/dist-packages/tensorpack/input_source/input_source.py", line 235, in _create_ema_callback size_ema_op = add_moving_summary(size, collection=None, decay=0.5)[0].op File "/usr/local/lib/python2.7/dist-packages/tensorpack/tfutils/summary.py", line 222, in add_moving_summary ctx = get_current_tower_context() File "/usr/local/lib/python2.7/dist-packages/tensorpack/tfutils/tower.py", line 222, in get_current_tower_context assert _CurrentTowerContext is not None, "The function is supposed to be called under a TowerContext!" AssertionError: The function is supposed to be called under a TowerContext!

[jiqizaisikao]

If we train the model on GPU ,could it predict on cpu?

[carlfm01]

@jiqizaisikao Yes, but it will be slow, for me a 7s audio took 40s on a Tesla k80