Files
HuggingFace_transformer/transformers
Diganta Misra 070dcf1c02 Added Mish Activation Function
Mish is a new activation function proposed here - https://arxiv.org/abs/1908.08681
It has seen some recent success and has been adopted in SpaCy, Thic, TensorFlow Addons and FastAI-dev. 
All benchmarks recorded till now (including against ReLU, Swish and GELU) is present in the repository - https://github.com/digantamisra98/Mish
Might be a good addition to experiment with especially in the Bert Model.
2019-11-07 03:45:43 +05:30
..
2019-10-24 21:43:28 +00:00
2019-11-06 14:03:47 -05:00
2019-10-09 11:07:43 +02:00
2019-11-05 13:31:58 -05:00
2019-10-03 22:29:03 -07:00
2019-10-29 17:10:20 +01:00
2019-11-05 13:31:58 -05:00
2019-10-11 16:05:30 -04:00
2019-11-04 17:19:15 +00:00
2019-11-05 19:06:12 -05:00
2019-11-05 13:31:58 -05:00
2019-10-22 14:12:33 -04:00