DKVMN
DKVMN copied to clipboard
Accessing values at internal nodes and carry over of value matrix values
I really liked the DKVMN model and wished to extend it further. I have read the code in detail and had some doubts:
- Does the value matrix re-initialize every batch or are the values carried over?
- Can the values at an internal node (Let's say the last fully connected layer) be I would be really grateful if you could help me in answering this
- Yes, the value matrix needs to re-initialize every batch.
- I'm sorry I don't quite understand your question.
I am sorry I didn't complete the question. I wanted to ask if we can access the values of the internal variables in the network at training / testing time. For example the values in the 'memory_value" i.e it the value matrix in memory.py
I can access the values of the params that are saved/loaded by save_checkpoint but not other internal values
@ritwickchaudhry You may refer to the discussion here. https://github.com/dmlc/mxnet/issues/4805