check this one

Solved!
Posted in General by kwang nam Wed Jul 29 2015 09:53:40 GMT+0000 (UTC)·2·Viewed 1,570 times

I got this error, Now I am using phthon 2.7 INFO:opendeep.optimization.optimizer:Initializing optimizer <class 'opendeep.optimization.adadelta.AdaDelta'> INFO:opendeep.optimization.optimizer:Optimizer config args: {'grad_clip': None, 'save_freq': 1000000, 'min_batch_size': 1, 'stop_threshold': inf, 'decay': 0.95, 'hard_clip': False, 'learning_rate': 1e-06, 'batch_size': 100, 'stop_patience': 1, 'epochs': 10, 'lr_decay': None, 'model': <opendeep.data.standard_datasets.image.mnist.MNIST object at 0x00000000143F7630>, 'dataset': <opendeep.models.single_layer.autoencoder.DenoisingAutoencoder object at 0x00000000233BDA58>, 'lr_decay_factor': None} Traceback (most recent call last): File "E:\project_luna\cuda\open_deep\test\opendeeptest2.py", line 29, in <module> optimizer = AdaDelta(dae, mnist) File "F:\python27\python-2.7.9.amd64\lib\site-packages\opendeep-0.0.9a0-py2.7.egg\opendeep\optimization\adadelta.py", line 72, in __init__ super(AdaDelta, self).__init__(**initial_parameters) File "F:\python27\python-2.7.9.amd64\lib\site-packages\opendeep-0.0.9a0-py2.7.egg\opendeep\optimization\optimizer.py", line 123, in __init__ "Found %s" % str(type(model)) AssertionError: Optimizer input model needs to be a Model class! Found <class 'opendeep.data.standard_datasets.image.mnist.MNIST'>
Markus Beissinger
July 29, 2015

In version 0.0.9a the ordering of those arguments has changed to dataset, model. To be safe you can name the arguments AdaDelta(model=dae, dataset=mnist). The documentation is currently in the process of being updated to the new version.

Markus Beissinger
July 29, 2015

In version 0.0.9a the ordering of those arguments has changed to dataset, model. To be safe you can name the arguments AdaDelta(model=dae, dataset=mnist). The documentation is currently in the process of being updated to the new version.


Markus Beissinger marked this as solved
Markdown is allowed