azaion/detections

mirror of https://github.com/azaion/detections.git synced 2026-04-22 05:26:32 +00:00

T

Oleksandr Bezdieniezhnykh 3984507221 [AZ-180] Fix INT8 conversion: set FP16 flag alongside INT8 for TensorRT 10.x

In TensorRT 10.x, INT8 conversion requires FP16 to be set as a fallback for
network layers (e.g. normalization ops in detection models) that have no INT8
kernel implementation. Without FP16, build_serialized_network can return None
on Jetson for YOLO-type models. INT8 flag is still the primary precision;
FP16 is only the layer-level fallback within the same engine.

Made-with: Cursor

2026-04-02 07:32:16 +03:00

[AZ-180] Update module and component docs for Jetson/INT8 changes

2026-04-02 07:25:22 +03:00

[AZ-178] Implement streaming video detection endpoint

2026-04-01 03:11:43 +03:00

Update .gitignore to include additional file types and directories for Python projects, enhancing environment management and build artifacts exclusion.

2026-03-20 21:28:16 +02:00

[AZ-178] Fix Critical/High security findings: auth, CVEs, non-root containers, per-job SSE

2026-04-02 06:32:12 +03:00

Refactor type casting in Cython files for improved clarity and consistency

2026-03-30 06:17:16 +03:00

[AZ-178] Implement streaming video detection endpoint

2026-04-01 03:11:43 +03:00

[AZ-180] Fix INT8 conversion: set FP16 flag alongside INT8 for TensorRT 10.x

2026-04-02 07:32:16 +03:00

[AZ-180] Fix INT8 conversion: set FP16 flag alongside INT8 for TensorRT 10.x

2026-04-02 07:32:16 +03:00

.env.example

[AZ-178] Fix Critical/High security findings: auth, CVEs, non-root containers, per-job SSE

2026-04-02 06:32:12 +03:00

.gitignore

[AZ-178] Fix Critical/High security findings: auth, CVEs, non-root containers, per-job SSE

2026-04-02 06:32:12 +03:00

AGENTS.md

Refactor autopilot workflows and documentation: Update .gitignore to include binary and media file types, enhance agent command references in documentation, and modify annotation class for improved accessibility. Adjust inference processing to handle batch sizes and streamline test specifications for clarity and consistency across the system.

2026-03-25 05:26:19 +02:00

classes.json

Refactor inference engine and task management: Remove obsolete inference engine and ONNX engine files, update inference processing to utilize batch handling, and enhance task management structure in documentation. Adjust paths for task specifications to align with new directory organization.

2026-03-28 01:04:28 +02:00

conftest.py

[AZ-178] Add real-video streaming test, update e2e tests, mark task done

2026-04-01 05:02:25 +03:00

docker-compose.jetson.yml

[AZ-180] Add Jetson Orin Nano support with INT8 TensorRT engine

2026-04-02 07:12:45 +03:00

Dockerfile

[AZ-178] Fix Critical/High security findings: auth, CVEs, non-root containers, per-job SSE

2026-04-02 06:32:12 +03:00

Dockerfile.gpu

[AZ-178] Fix Critical/High security findings: auth, CVEs, non-root containers, per-job SSE

2026-04-02 06:32:12 +03:00

Dockerfile.jetson

[AZ-180] Add Jetson Orin Nano support with INT8 TensorRT engine

2026-04-02 07:12:45 +03:00

README.md

Initial commit

2026-03-17 19:15:55 +02:00

requirements-gpu.txt

Initial commit

2026-03-17 19:15:55 +02:00

requirements-jetson.txt

[AZ-180] Add Jetson Orin Nano support with INT8 TensorRT engine

2026-04-02 07:12:45 +03:00

requirements-macos.txt

fix some cython code

2026-03-29 21:18:18 +03:00

requirements.txt

[AZ-178] Fix Critical/High security findings: auth, CVEs, non-root containers, per-job SSE

2026-04-02 06:32:12 +03:00

run-tests.sh

[AZ-178] Fix Critical/High security findings: auth, CVEs, non-root containers, per-job SSE

2026-04-02 06:32:12 +03:00

setup.py

Add AIAvailabilityStatus and AIRecognitionConfig classes for AI model management

2026-03-31 05:49:51 +03:00

README.md

Azaion.Detections

Cython/Python service for YOLO inference (TensorRT / ONNX Runtime). GPU-enabled container.