CODEWITHSUNDEEP
neural-networkdeep-learningcaffelstmrecurrent-neural-network
bossman
bossman

Reputation: 340

Message type "caffe.LayerParameter" has no field named "lstm_param"

I was trying to run the LRCN example from Jeff Donahue's recurrent-rebase-cleanup branch of Caffe. I have installed the latest caffe version from the master branch. According to my knowledge Caffe now supports LSTM layers. But when I run the solver I get this error. Is the name of the field wrong? If so then what is the correct field name and how can I find caffe layer parameter & field names for future use?

I also tried running with the parameter name as recurrent_param but still get the same error.

Upvotes: 0

Views: 1792

Answers (1)

Shai
Shai

Reputation: 114786

If you are using "LSTM" layer from the latest "master" branch, you need to use recurrent_param instead of lstm_param.
For more information see caffe.help.

Generally speaking, if you are trying to run a model build in a specific branch of caffe, you should build and use caffe of that specific branch as layer names/parameters may vary across branches (as it seems to be the case here)

Upvotes: 2

Related Questions