[GitHub] train-test-laura commented on issue #7364: MxnetR chunk-wise neural nets
train-test-laura commented on issue #7364: MxnetR chunk-wise neural nets URL: https://github.com/apache/incubator-mxnet/issues/7364#issuecomment-321505488 Hi Thirdwind, thank you very much - this seems to be exactly what I was looking for. That is easier than I expected it to be - just taking arg.params and aux.params from model 1 (chunk 1) and take it to model 2 (chunk 2) and so on - great! This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] train-test-laura commented on issue #7364: MxnetR chunk-wise neural nets
train-test-laura commented on issue #7364: MxnetR chunk-wise neural nets URL: https://github.com/apache/incubator-mxnet/issues/7364#issuecomment-320941845 Thanks for your reply. I have found that page already pretty helpful, but there are a few questions I have - maybe you or someone else could help me. First of, I am not sure what the output named "flatten_output" is - I thought for me it could be softmax_output as well, not sure. There, I am also not sure what to put in "Input Shape". - the dimensions of the original data set? the dimensions of the neural net? I am lost... Any help would be great! Thanks Laura This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] train-test-laura commented on issue #7364: MxnetR chunk-wise neural nets
train-test-laura commented on issue #7364: MxnetR chunk-wise neural nets URL: https://github.com/apache/incubator-mxnet/issues/7364#issuecomment-320941845 Thanks for your reply. I have found that page already pretty helpful, but there are a few questions I have - maybe you or someone else could help me. First of, I am not sure what the output named "flatten_output" is - I thought for me it could be softmax_output as well, not sure. For mx.model.init.params: I get the error: could not find function "mx.model.init.params" There, I am also not sure what to put in "Input Shape". - the dimensions of the original data set? the dimensions of the neural net? I am lost... Any help would be great! Thanks Laura This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
