v0.6.2 Python 3.10 support

Release 0.6.2

---

Bug Fixes and Other Improvements

• Add support for Python 3.10, drop support for Python 3.6.
• Bump requirements to latest versions.
• Update Raspberry Pi and setup install to latest tensorflow-lite guidance.

v0.6.1 Fix for TFLite and ONNX image model predict error

Release 0.6.1

Bug Fixes and Other Improvements

Fix super invocations for onnx and tflite backends -- Calling predict() was broken because self.lock has not been
assigned.

v0.6.0 Heatmap visualizations via Grad-CAM++ and backend base class refactor

Release 0.6.0

---

Breaking Changes

• Refactored the ML backends into sub-folders:
  • TFModel class: backends/backend_tf.py -> backends/tf/backend.py
  • TFLiteModel class: backends/backend_tflite.py -> backends/tflite/backend.py
  • ONNXModel class: backends/backend_onnx.py -> backends/onnx/backend.py

Bug Fixes and Other Improvements

• Added Backend and ImageBackend abstract base classes in backends/backend.py
• Added ImageBackend classes for each ML backend:
  • TFImageModel class: backends/tf/image_backend.py
  • TFLiteImageModel class: backends/tflite/image_backend.py
  • ONNXImageModel class: backends/onnx/image_backend.py
• Added Grad-CAM++ implementation (ImageBackend.gradcam_plusplus(image, label) -> np.ndarray) for visualizing
  convolutional neural network heatmaps for explaining why the model predicted a certain label.
  Note: Grad-CAM++ only implemented currently in TFImageModel for TensorFlow Lobe model exports.
  The visualization can be called from the top-level API of ImageModel -> ImageModel.visualize(image)

v0.5.0 Modular machine learning backend install via pip options

Release 0.5.0

---

Breaking Changes

• Install Lobe with your desired backend options through pip -- pip install lobe[all] for everything,
  pip install lobe[tf] for tensorflow, pip install --index-url https://google-coral.github.io/py-repo/ tflite_runtime; pip install lobe for tensorflow lite, pip install lobe[onnx] for onnx.

v0.4.0 Backwards compatibility for Lobe model exports, fix API client return signature.

Release 0.4.0

---

Bug Fixes and Other Improvements

• Fix API return signature for Lobe 0.9
• Make backwards-compatible with earlier versions of model exports

v0.3.0 Fix backwards-compatibility, add ONNX, refactor

Release 0.3.0

Breaking Changes

• Previous use of Signature should be ImageClassificationSignature. from lobe.signature import Signature ->
  from lobe.signature import ImageClassificationSignature

Bug Fixes and Other Improvements

• Update to TensorFlow 2.4 from 1.15.4
• Add ONNX runtime backend
• Use requests instead of urllib
• Make backends thread-safe
• Added constants file for signature keys to enable backwards-compatibility

v0.2.1: fix signature bugs (#10)

* fix signature bugs

* Update setup.py

v0.2.0: Merge pull request #9 from lobe/aa-pypi-release

create publishing action for pypi