0.4.0 (01/06/2022) Pose Detection, EfficientDet for Object Detection and EfficientNet for Image Recognition
Features:
- Added the PoseNet model family to the ONNX Model Hub. #269
- MoveNetSinglePoseLighting
- MoveNetMultiPoseLighting
- MoveNetSinglePoseThunder
- Added the EfficientDet model family to the ONNX Model Hub. #304
- EfficientDetD0
- EfficientDetD1
- EfficientDetD2
- EfficientDetD3
- EfficientDetD4
- EfficientDetD5
- EfficientDetD6
- Added SSD-Mobilenet-v1 model to the ONNX Model Hub. #296
- Added EfficientNet model family to the ONNX Model Hub. #264
- EfficientNetB0 ( + noTop model)
- EfficientNetB1 ( + noTop model)
- EfficientNetB2 ( + noTop model)
- EfficientNetB3 ( + noTop model)
- EfficientNetB4 ( + noTop model)
- EfficientNetB5 ( + noTop model)
- EfficientNetB6 ( + noTop model)
- EfficientNetB7 ( + noTop model)
- Added NoTop models to the TensorFlow Model Hub. #281
- VGG'16
- VGG'19
- ResNet50
- ResNet101
- ResNet152
- ResNet50V2
- ResNet101V2
- ResNet152V2
- MobileNet
- MobileNetV2
- NasNetMobile
- NasNetLarge
- DenseNet121
- DenseNet169
- DenseNet201
- Xception
- Inception
- Added new
Dot
layer andConv1DTranspose
,Conv2DTranspose
,Conv3DTranspose
layers.
#144 #124 - Added new activation functions:
SparsemaxActivation
andSoftShrinkActivation
.
#171 #170 - Added new
Padding
,CenterCrop
,Convert
,Grayscale
image preprocessors andNormalizing
tensor preprocessor.
#203 #201
#202 #204
Examples and tutorials:
- Added an example of Image preprocessing DSL usage with TensorFlow model. #292.
- Added examples for Object Detection with EfficientDet2.
- Added examples for Object Detection with SSD-Mobilenet-v1.
- Added examples for Pose Detection with different models.
- Added examples for Image Recognition with different models from EfficientNet model family.
- Added examples for fine-tuning of noTop ResNet model.
- Added an example for new Image Preprocessing DSL operator Normalize.
- Added an example for Linear Regression model training with two metrics.
- Added an example for new Functional API DSL with ToyResNet model.
- Added an example for training LeNet model with multiple callbacks support.
API changes:
- Introduced new DSL for creating
Sequential
andFunctional
models. #133 - Added support for multiple
Callbacks
infit()
,evaluate()
,predict()
instead ofcompile()
.
#270 - Added support for multiple metrics. #298
- Added support for the model reset. #271
- Replaced
Long
parameters withInteger
ones in convolutional, average pool and max pool layers.
#273 - Moved loading section out of image preprocessing. #322
- Remove obsolete
CustomPreprocessor
interface. #257 - Supported exporting tensor data to
BufferedImage
#293
Internal API changes:
- Introduced new abstraction for layer parameters --
KVariable
. #324 - Moved some of the
Layer
functionality to the new interfacesParametrizedLayer
andTrainableLayer
.
#217
Bug fixes:
- Added support for correct loading of
isTrainable
status from Keras. #153 - Generalized
Reshape
layer to higher dimensions. #249 - Fixed incorrect bounding box coordinates in ObjectDetection and FaceDetection examples. #279
- Fixed
toString
methods for layer classes. #301 - Set all the optimizers to have
useLocking = True
#305 - Fixed a bug with silently skipped layers in topological sort. #314
- Fixed
loadModelLayersFromConfiguration
recursively calling itself. #319 - Fixed
GraphTrainableModel#internalPredict
for multi-dimensional predictions. #327 - Fixed
Orthogonal
initializer. #348 - Fixed initialization of the variables in
GraphTrainableModel
. #355 - Add model output type checks for
OnnxInferenceModel
. #356 - Fixed
IndexOutOfBoundsException
in theDot
layer. #357 - Fixed import and export issues:
- Updated log4j version.
- Fixed the group of examples with ToyResNet.
Thanks to our contributors:
- Alexey Zinoviev (@zaleslaw)
- Julia Beliaeva (@juliabeliaeva)
- Ansh Tyagi (@therealansh)
- Veniamin Viflyantsev (@knok16)
- @cagriyildirimR
- Wu Han (@wuhanstudio)
- Michal Harakal (@michalharakal)
- xiaoshen (@smallshen)
- @ermolenkodev