JamesDestiny
commented
2 years ago how can i access to wget http://dataset.cs.mcgill.ca/ubuntu-corpus-1.0/ubuntu_blobs.tgz
Open DeepInEvil opened 6 years ago
JamesDestiny
commented
2 years ago how can i access to wget http://dataset.cs.mcgill.ca/ubuntu-corpus-1.0/ubuntu_blobs.tgz
We are getting this error while running the code, seems like some problem with the update. Please check
% "\n\t".join(suggestions)) total_params: 44298600 Traceback (most recent call last): File "main.py", line 669, in
main()
File "main.py", line 661, in main
model = Model(**args.dict)
File "main.py", line 375, in init
self.update_params()
File "main.py", line 408, in update_params
self.train_model = theano.function([], self.cost, updates=updates, givens=givens, on_unused_input='warn')
File "/home/DebanjanChaudhuri/anaconda3/envs/chatbot_exp/lib/python2.7/site-packages/theano/compile/function.py", line 317, in function
output_keys=output_keys)
File "/home/DebanjanChaudhuri/anaconda3/envs/chatbot_exp/lib/python2.7/site-packages/theano/compile/pfunc.py", line 449, in pfunc
no_default_updates=no_default_updates)
File "/home/DebanjanChaudhuri/anaconda3/envs/chatbot_exp/lib/python2.7/site-packages/theano/compile/pfunc.py", line 208, in rebuild_collect_shared
raise TypeError(err_msg, err_sug)
TypeError: ('An update must have the same type as the original shared variable (shared_var=cell_init, shared_var.type=TensorType(float64, row), update_val=Elemwise{sub,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.')
Regards, Debanjan