0.4.2

What's Changed

• Fix DynamicApp parameters are not accurate
  • args -> kwargs
  • add args tuple
• Fix some typing and hints

0.4.1

What's Changed

• fix(package): move the project source code from src
• feat(Dynamic): add dynamic import process and set recording_path
• chore: update examples & README.md

0.4.0

What't Changed

• 💥Broken refactor(typo): specification of variable names adds typing
• 💥Broken refactor(Dispatcher): streamline the Dispatcher implementation, remove collect_results and move to DevelopDispatcher
• feat: added DynamicApp to support dynamically running inference tasks through configuration
• typo(Streamlit): rename the streamlit app file to streamlit_.py instead of server.py
• chore: update examples

0.3.2

What's Changed

• chore(Dispatcher): Set the default max_size of Dispatcher to 30
• feat(Player): Added tqdm for limited length video progress printing
• feat(Timer): The timeout warning is added to the inference Timer in real-time inference
• feat(Dispatcher): Run the Inference algo frame_step set to 0

0.3.0

What's Changed

• feat(Dispatcher): using the factory mode simplifies instantiation of the Dispatcher
• feat(Recorder): supports offline inference to record video files to disk according to different producers
• package: separate version

0.2.3

• Fix(Player): number of frames under real-time inference does not correspond to time
• Feat(Server): support for loading live streams and producer selection

0.2.2

• Add current_algo_names to process_func for offline inference to know the current inference algorithm in flow.

0.2.1

• Fix typo: progress -> process ....

0.2.0

• Feat: The start() function is added to Inference, simplifying and unifying the way offline and real-time inference run.
• Feat: Use wrapper callback instead of inheritance:
  • Inference: set_custom_progress()
  • Server: set_annotate_frame() and set_output()

streamlit_service_app.mp4

0.1.3

• Added streamlit service app to customize drawing and output components => Streamlit Debug
• Fixed an issue where multiple inferences could not coexist due to auto_run_specific return in offline inferences

streamlit_service_app.mp4