Theano error about video-description-with-spatial-temporal-attention HOT 6 CLOSED

TypeError: Cannot convert Type TensorType(float64, matrix) (of Variable Elemwise{add,no_inplace}.0) into Type TensorType(float32, matrix). You can try to manually convert Elemwise{add,no_inplace}.0 into a TensorType(float32, matrix).

During handling of the above exception, another exception occurred:

TypeError: ('An update must have the same type as the original shared variable (shared_var=Wemb_rgrad2, shared_var.type=TensorType(float32, matrix), update_val=Elemwise{add,no_inplace}.0, update_val.type=TensorType(float64, matrix)).', 'If the difference is related to the broadcast pattern, you can call the tensor.unbroadcast(var, axis_to_unbroadcast[, ...]) function to remove broadcastable dimensions.')

from video-description-with-spatial-temporal-attention.

This project is implemented on linux system, and you should use the same environment as well.

from video-description-with-spatial-temporal-attention.

from video-description-with-spatial-temporal-attention.

Please give solution for it

from video-description-with-spatial-temporal-attention.

And Sir, tell me this also

Now ready to launch the training

$ THEANO_FLAGS=mode=FAST_RUN,device=cuda0,floatX=float32 python train_model.py

how can i use this?

from video-description-with-spatial-temporal-attention.

You should first "cd " into the directory containing train.py and use this command in linux shell

from video-description-with-spatial-temporal-attention.