[Init] Initial commit for Synaptics SL1680 NPU (#19680)

* [Init] Initial commit for Synaptics SL1680 NPU

* add a rough detector which is testing with yolov8 tflite model.

* [Feat] Add dependencies installation in docker build

- Add runtime library and wheels installation in main/Dockerfile
- Add model.synap(default model, transfer from mobilenet_224full80) in docker/synap1680

* [Update] Remove dependencies installation from main Dockerfile

- remove deps installation from Dockerfile
- add dependencies installation and split wheels, deps stage in synap1680 Dockerfile

* Refactor synap detector to more closely match other implementations

* [Update] Add model path configuration check

* [Update] update ModelType to ssd

* [Update] Remove unuse script

- install_deps.sh has already been executing in deps download stage
- Dockerfile.toolchain is for testing to extract runtime libraries from Synaptics toolchain

* [Update] update Synaptics SL1680 setup description

* [Update] remove install_synap1680

- The deps download and installation is existed in synap1680

* [Fix] update document content

* [Update] Update detector from synap1680 to synaptics

This update is in order to make the synaptics SL-series NPU detector more general.

- Fix detector `os` module not import bug
- Update detector type `synap1680` to `synaptics`
- Update document description `SL1680` to `Synaptics` only
- Update docker build content `synap1680` to `synaptics`

* [Fix] Update configuration document

* Update docs/docs/configuration/object_detectors.md

Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>

* [Update] Update document content and detector default layout

- Update object_detectors document
- Update detector's default layout
- Update default model name

* [Update] Update object detector document content

* [Fix] Fix InputTensorEnum not defined error

- import InputTensorEnum from detector_config

* [Update] Update detector script coding format

* [Update] Update synaptics detector coding format

* [Update] Add synaptics ci workflow

* [Update] update synaptics runtime libs download path

- Fork Synaptics astra sdk repo and put the runtime lib package on it
- Frigate team can update this download path later

---------

Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>

frigate/detectors/plugins/synaptics.py

@@ -0,0 +1,91 @@
+import logging
+import os
+
+import numpy as np
+from synap import Network
+from synap.postprocessor import Detector
+from synap.preprocessor import Preprocessor
+from synap.types import Layout, Shape
+from typing_extensions import Literal
+
+from frigate.detectors.detection_api import DetectionApi
+from frigate.detectors.detector_config import (
+    BaseDetectorConfig,
+    InputTensorEnum,
+    ModelTypeEnum,
+)
+
+logger = logging.getLogger(__name__)
+
+DETECTOR_KEY = "synaptics"
+
+
+class SynapDetectorConfig(BaseDetectorConfig):
+    type: Literal[DETECTOR_KEY]
+
+
+class SynapDetector(DetectionApi):
+    type_key = DETECTOR_KEY
+
+    def __init__(self, detector_config: SynapDetectorConfig):
+        try:
+            _, ext = os.path.splitext(detector_config.model.path)
+            if ext and ext != ".synap":
+                raise ValueError("Model path config for Synap1680 is wrong.")
+
+            synap_network = Network(detector_config.model.path)
+            logger.info(f"Synap NPU loaded model: {detector_config.model.path}")
+        except ValueError as ve:
+            logger.error(f"Config to Synap1680 was Failed: {ve}")
+            raise
+        except Exception as e:
+            logger.error(f"Failed to init Synap NPU: {e}")
+            raise
+
+        self.width = detector_config.model.width
+        self.height = detector_config.model.height
+        self.model_type = detector_config.model.model_type
+        self.network = synap_network
+        self.network_input_details = self.network.inputs[0]
+        self.input_tensor_layout = detector_config.model.input_tensor
+
+        # Create Inference Engine
+        self.preprocessor = Preprocessor()
+        self.detector = Detector(score_threshold=0.4, iou_threshold=0.4)
+
+    def detect_raw(self, tensor_input: np.ndarray):
+        # It has only been testing for pre-converted mobilenet80 .tflite -> .synap model currently
+        layout = Layout.nhwc  # default layout
+        detections = np.zeros((20, 6), np.float32)
+
+        if self.input_tensor_layout == InputTensorEnum.nhwc:
+            layout = Layout.nhwc
+
+        postprocess_data = self.preprocessor.assign(
+            self.network.inputs, tensor_input, Shape(tensor_input.shape), layout
+        )
+        output_tensor_obj = self.network.predict()
+        output = self.detector.process(output_tensor_obj, postprocess_data)
+
+        if self.model_type == ModelTypeEnum.ssd:
+            for i, item in enumerate(output.items):
+                if i == 20:
+                    break
+
+                bb = item.bounding_box
+                # Convert corner coordinates to normalized [0,1] range
+                x1 = bb.origin.x / self.width  # Top-left X
+                y1 = bb.origin.y / self.height  # Top-left Y
+                x2 = (bb.origin.x + bb.size.x) / self.width  # Bottom-right X
+                y2 = (bb.origin.y + bb.size.y) / self.height  # Bottom-right Y
+                detections[i] = [
+                    item.class_index,
+                    float(item.confidence),
+                    y1,
+                    x1,
+                    y2,
+                    x2,
+                ]
+        else:
+            logger.error(f"Unsupported model type: {self.model_type}")
+        return detections