issues
search
HunterMcGushion
/
hyperparameter_hunter
Easy hyperparameter optimization and automatic result saving across machine learning algorithms and libraries
MIT License
706
stars
100
forks
source link
Keras `Embedding` layers with initialized weights
#123
Open
HunterMcGushion
opened
5 years ago
HunterMcGushion
commented
5 years ago
Embedding
layer can’t be given initialized weights
Embedding
alone works if it initializes own weights
Needs function parameters to be given weight initialization
Note
This issue (along with several others) was originally opened by @caprone in #111, but it is being moved here for easier tracking
If this issue is missing any important information from #111, please feel free to mention/paste it
Embeddinglayer can’t be given initialized weightsEmbeddingalone works if it initializes own weightsNote