There are 0 repository under dynamic-batch-size topic.
Neutron: A pytorch based implementation of Transformer and its variants.
Increase the inference speed of the model
Export pytorch model to ONNX and convert ONNX from float32 to float 16
Important vs Ignore email classifier based on incoming email addresses. Bert tokenizer is used as a tokenization method and CNN network as the model. Framework used - Tensorflow 2.4