titu1994 / Super-Resolution-using-Generative-Adversarial-Networks

An implementation of SRGAN model in Keras
283 stars 85 forks source link

Using new modle.py it occurs error to theano.gof.fg.MissingInputError #13

Closed eeric closed 8 years ago

eeric commented 8 years ago

--Traceback (most recent call last): File "models.py", line 729, in srgan_network.train_full_model(coco_path, nb_images=4400, nb_epochs=5) File "models.py", line 437, in train_full_model self._train_model(image_dir, nb_images, nb_epochs, load_generative_weights=True, load_discriminator_weights=True) File "models.py", line 635, in _train_model batch_size=self.batch_size, nb_epoch=1, verbose=0) File "/home/yq/work/Super-Resolution-using-Generative-Adversarial-Networks-master/keras_training_ops.py", line 158, in fit model._make_train_function() File "/usr/local/lib/python2.7/dist-packages/Keras-1.1.1-py2.7.egg/keras/engine/training.py", line 721, in _make_train_function self._function_kwargs) File "/usr/local/lib/python2.7/dist-packages/Keras-1.1.1-py2.7.egg/keras/backend/theano_backend.py", line 821, in function return Function(inputs, outputs, updates=updates, kwargs) File "/usr/local/lib/python2.7/dist-packages/Keras-1.1.1-py2.7.egg/keras/backend/theano_backend.py", line 807, in init **kwargs) File "/usr/local/lib/python2.7/dist-packages/theano/compile/function.py", line 320, in function output_keys=output_keys) File "/usr/local/lib/python2.7/dist-packages/theano/compile/pfunc.py", line 479, in pfunc output_keys=output_keys) File "/usr/local/lib/python2.7/dist-packages/theano/compile/function_module.py", line 1776, in orig_function output_keys=output_keys).create( File "/usr/local/lib/python2.7/dist-packages/theano/compile/function_module.py", line 1428, in init accept_inplace) File "/usr/local/lib/python2.7/dist-packages/theano/compile/function_module.py", line 177, in std_fgraph update_mapping=update_mapping) File "/usr/local/lib/python2.7/dist-packages/theano/gof/fg.py", line 171, in init self.import_r(output, reason="init") File "/usr/local/lib/python2.7/dist-packages/theano/gof/fg.py", line 360, in import_r self.import(variable.owner, reason=reason) File "/usr/local/lib/python2.7/dist-packages/theano/gof/fg.py", line 474, in import r) theano.gof.fg.MissingInputError: ("An input of the graph, used to compute Elemwise{true_div,no_inplace}(x_discriminator, DimShuffle{x,x,x,x}.0), was not provided and not given a value.Use the Theano flag exception_verbosity='high',for more information on this error.", x_discriminator)

--There is a same error to delete 719th and (or) 720th line, why?