DJL v0.11.0 brings the new engines XGBoost 1.3.1, updates PyTorch to 1.8.1, TensorFlow to 2.4.1, Apache MXNet 1.8.0, PaddlePaddle to 2.0.2 and introduces several new features:

Key Features

• Supports XGBoost 1.3.1 engine inference: now you can run prediction using models trained in XGBoost.
• Upgrades PyTorch to 1.8.1 with CUDA 11.1 support.
• Upgrades TensorFlow to 2.4.1 with CUDA 11.0 support.
• Upgrades Apache MXNet to 1.8.0 with CUDA 11.0 support.
• Upgrades PaddlePaddle to 2.0.2.
• Upgrades SentencePiece to 0.1.95.
• Introduces the djl-serving brew package: now you can install djl-serving with brew install djl-serving.
• Introduces the djl-serving plugins.
• Introduces Amazon Elastic Inference support.

Enhancement

• Improves TensorFlow performance by reducing GC and fixed memory leaking issue (#892)
• djl-serving now can run all the engines out-of-box (#886)
• Improves DJL training by using multi-threading on each GPU (#743)
• Implements several operators:
  • Adds boolean set method to NDArray (#784)
  • Adds batch dot product operator (#849)
  • Adds norm operator to PyTorch (#692)
  • Adds one hot operator (#684)
  • Adds weight decay to Loss (#788)
• Adds setGraphExecutorOptimize option for PyTorch engine. (#904)
• Introduces String tensor support for ONNXRuntime (#724)
• Introduces several API improvements
  • Creates ObjectDetectionDataset (#683)
  • Improves Block usability (#712)
  • Adds BlockFactory feature in model loading (#805)
  • Allows PyTorch stream model loading (#729)
  • Adds NDList decode from InputStream (#734)
  • Adds SymbolBlock Serialization (#687)
• Introduces model searching feature in djl central (#799)

Documentation and examples

• Introduces DJL tutorials - How to load model on DJL Youtube Channel
• Adds the PaddlePaddle load model documentation (#811)
• Adds the documentations for profiler (#722)
• Adds face detection and face recognition examples (#814)
• Adds model training visualization demo using Vue

Breaking change

• Renames CheckpointsTrainingListener to SaveModelTrainingListener (#686)
• Removes erroneous random forest application (#726)
• Deletes DataManager class (#691)
• Classes under ai.djl.basicdataset packages has been moved into each sub-packages.

Bug Fixes

• Fixes BufferOverflowException when handling handling subimage (#866)
• Fixes ONNXRuntime 2nd engine dependency from IrisTranslator (#853)
• Fixes sequenceMask error when n dimension is 2 (#828)
• Fixes TCP port range buf in djl-serving (#773)
• Fixes one array case for concat operator (#739)
• Fixes non-zero operator for PyTorch (#704)

Known issues

• TensorFlow engine has known memory leak issue due to JavaCPP dependency. The memory leak issue has been fixed in javacpp 1.5.6-SNAPSHOT. User has to manually include javacpp 1.5.6-SNAPSHOT to avoid memory leak. See: https://github.com/deepjavalibrary/djl/tree/master/tensorflow/tensorflow-engine#installation for more detail.

Contributors

This release is thanks to the following contributors:

• Akshay Rajvanshi(@aksrajvanshi (https://github.com/ghost))
• Anthony Feenster(@anfee1 (https://github.com/anfee1))
• Calvin(@mymagicpower (https://github.com/mymagicpower))
• enpasos(@enpasos (https://github.com/enpasos))
• Erik Bamberg(@ebamberg (https://github.com/ebamberg))
• Frank Liu(@frankfliu (https://github.com/frankfliu))
• G Goswami(@goswamig (https://github.com/goswamig))
• Hugo Miguel Ferreira(@hmf (https://github.com/hmf))
• Hodovo(@hodovo (https://github.com/Hodovo))
• Jake Lee(@stu1130 (https://github.com/stu1130))
• Lai Wei(@roywei (https://github.com/roywei))
• Qing Lan(@lanking520 (https://github.com/lanking520))
• Marcos(@markbookk (https://github.com/markbookk))
• Stan Kirdey(@skirdey (https://github.com/skirdey))
• Zach Kimberg(@zachgk (https://github.com/zachgk))
• 付颖志 (@fuyz (https://github.com/fuyz))
• 石晓伟(@Shixiaowei02 (https://github.com/Shixiaowei02))