Resource
NVIDIA
GNMT v2 for PyTorchThe GNMT v2 model is an improved version of the first Google's Neural Machine Translation System with a modified attention mechanism.
Copied!
Changelog
- Aug 7, 2018
- Initial release
- Dec 4, 2018
- Added exponential warm-up and step learning rate decay
- Multi-GPU (distributed) inference and validation
- Default container updated to NGC PyTorch 18.11-py3
- General performance improvements
- Feb 14, 2019
- Different batching algorithm (bucketing with 5 equal-width buckets)
- Additional dropouts before first LSTM layer in encoder and in decoder
- Weight initialization changed to uniform (-0.1,0.1)
- Switched order of dropout and concatenation with attention in decoder
- Default container updated to NGC PyTorch 19.01-py3
- Jun 25, 2019
- Default container updated to NGC PyTorch 19.05-py3
- Mixed precision training implemented using APEX AMP
- Added inference throughput and latency results on NVIDIA Tesla V100 16G
- Added option to run inference on user-provided raw input text from command line
Known issues
There are no known issues in this release.