I am trying to run 5_caption_conditional_sampling.sh, but it gives this error
F0311 20:36:36.194001 12299 embed_layer.cu:61] Check failed: !propagate_down[0] Can't backpropagate to EmbedLayer input.
I am using cuda8 and cudnn, and the lastes version of Caffe from git which already includes RNN, LSTM layers in master branch
See https://github.com/anguyen8/caffe_lrcn is a clone of http://jeffdonahue.com/lrcn/ which has send pull request and already merged see:https://github.com/BVLC/caffe/pull/3948
I even tried to change _lrcn_word_topreds.deploy.prototxt file by adding
propagate_down: true
to
layer { name: "embedding" type: "Embed" propagate_down: true bottom: "input_sentence" top: "embedded_input_sentence" embed_param { input_dim: 8801 num_output: 1000 bias_term: false } }
Embed layer
But same error persists
Where am i doing wrong, am i just on the wrong track?
I am trying to run 5_caption_conditional_sampling.sh, but it gives this error
F0311 20:36:36.194001 12299 embed_layer.cu:61] Check failed: !propagate_down[0] Can't backpropagate to EmbedLayer input.
I am using cuda8 and cudnn, and the lastes version of Caffe from git which already includes RNN, LSTM layers in master branch See https://github.com/anguyen8/caffe_lrcn is a clone of http://jeffdonahue.com/lrcn/ which has send pull request and already merged see:https://github.com/BVLC/caffe/pull/3948I even tried to change _lrcn_word_topreds.deploy.prototxt file by adding
propagate_down: true
tolayer { name: "embedding" type: "Embed" propagate_down: true bottom: "input_sentence" top: "embedded_input_sentence" embed_param { input_dim: 8801 num_output: 1000 bias_term: false } }
Embed layer But same error persists Where am i doing wrong, am i just on the wrong track?