Through the study on OpenAI's model, here is some useful information for developers who wrote their own version of mlstm and try to import OpenAI's model paramters. In mlstm function in encoder.py, defines the tensors' name, this is the baseline.
Computation Graphic and tensor
Under the name scope model, there are three sub name scope:
embedding
tensors: w
out
tensors: w, b
rnn
tensors: b, gh, gmb, gmx, gx, wh, wmh, wmx, wx
The tensors are listed as follow:
tensor_name: model/embedding/w
tensor_name: model/out/b
tensor_name: model/out/w
tensor_name: model/rnn/b
tensor_name: model/rnn/gh
tensor_name: model/rnn/gmh
tensor_name: model/rnn/gmx
tensor_name: model/rnn/gx
tensor_name: model/rnn/wh
tensor_name: model/rnn/wmh
tensor_name: model/rnn/wmx
tensor_name: model/rnn/wx
Table for the correlation between tensor and .npy files
For detailed information about each tensor and which .npy it is correlated, please check the table
Line of code follows the openAI's orignal code repo.
Through the study on OpenAI's model, here is some useful information for developers who wrote their own version of mlstm and try to import OpenAI's model paramters. In mlstm function in encoder.py, defines the tensors' name, this is the baseline.
Computation Graphic and tensor Under the name scope model, there are three sub name scope:
Table for the correlation between tensor and .npy files For detailed information about each tensor and which .npy it is correlated, please check the table Line of code follows the openAI's orignal code repo.
Hopyfully this would help.