AdrienLE/learning_by_grad_by_grad_repro
Reproduction of "Learning to Learn by Gradient Descent by Gradient Descent"
Jupyter Notebook
Issues
- 0
Optimizer got an empty parameter list
#7 opened by BasitAlawode - 0
Application to new dataset
#6 opened by thomasarmstrong98 - 0
Any idea to scale up to complex networks?
#5 opened by chenwydj - 1
Code only supports toy examples and can be cleaned up by implementing zero_grad
#3 opened by alexvicegrab - 1
offset variable has not been updated
#2 opened by itongworld