NVIDIA Deep Learning Examples
Copied!
Resource
NVIDIA Deep Learning Examples
SIM for TensorFlow2Search-based Interest Model (SIM) is a system for predicting user behavior given sequences of previous interactions.
Copied!
Changelog
May 2022
- Initial release
November 2022
- Moved batching and padding operations to preprocessing
- Added support for prebatched samples during dataloading
- Reduced throughput variance (previously appearing mainly during inference)
Known issues
- The SIM model results are non-deterministic, even using the same random seed. The reason for this non-determinism is the tf.math.unsorted_segment_sum operation called within an optimization step. Its influence depends on categorical data distribution within a batch, and this issue is more severe for momentum-based optimizers. A potential solution is to use a deterministic version of this op which allows perfect reproduction, but is up to six times slower training.