Showing an error

[vinayakumarr]

How to correct the error. For detailed, please see the attached image

keras version 1.2.0
Theano version 0.8.2

[vinayakumarr]

This is because the the json files are loaded in a different version of theano and keras, So when i try to execute the training program, the program is working properly.

[vinayakumarr]

When i tireid to run the sudo python train_autoencoder.py, after 38 epochs i am getting the following below error. How to correct this?
I am using Version: 0.9.0.dev2 and keras Version: 1.1.1
File "train_autoencoder.py", line 301, in
limit=args.limit) # just train on first 5000 molecules for quick testing. set to None to use all 250k
File "train_autoencoder.py", line 275, in main
show_accuracy=True)
File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 627, in fit
sample_weight=sample_weight)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1124, in fit
callback_metrics=callback_metrics)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 862, in _fit_loop
callbacks.on_epoch_end(epoch, epoch_logs)
File "/usr/local/lib/python2.7/dist-packages/keras/callbacks.py", line 42, in on_epoch_end
callback.on_epoch_end(epoch, logs)
File "train_autoencoder.py", line 126, in on_epoch_end
index = sample(j, TEMPERATURE)
File "train_autoencoder.py", line 44, in sample
return np.argmax(np.random.multinomial(1, a, 1))
File "mtrand.pyx", line 4593, in mtrand.RandomState.multinomial (numpy/random/mtrand/mtrand.c:37541)
ValueError: sum(pvals[:-1]) > 1.0

[wadekun]

maybe you should install keras from here: https://github.com/rgbombarelli/keras
you should uninstall keras currently: pip uninstall keras, then

1. git clone https://github.com/rgbombarelli/keras.git
2. cd keras
3. python setup.py install

[xuzhang5788]

When I tried to run sample_autoencoder.py, I got the following error message.

Using Theano backend.
Using gpu device 0: GeForce GTX 1070 (CNMeM is enabled with initial size: 80.0% of memory, cuDNN 5005)
Traceback (most recent call last):
File "sample_autoencoder.py", line 96, in
model = model_from_json(json.dumps(model_dict))
File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 210, in model_from_json
return layer_from_config(config, custom_objects=custom_objects)
File "/usr/local/lib/python2.7/dist-packages/keras/utils/layer_utils.py", line 26, in layer_from_config
class_name = config['class_name']
KeyError: 'class_name'

[xuzhang5788]

When I ran train_autoencoder.py, after 100 epoches, I got val_loss: 0.9318 - val_acc: 0.7127, not like you said "Loss: 0.834809958935, Accuracy: 0.948206666667"