Upload 11 files

Dockerfile

@@ -0,0 +1,9 @@
+FROM nvcr.io/nvidia/tritonserver:23.02-py3
+
+# Install dependencies
+RUN pip install opencv-python && \
+    apt update && \
+    apt install -y libgl1 && \
+    rm -rf /var/lib/apt/lists/*
+
+CMD ["tritonserver", "--model-repository=/models" ]

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -1,14 +1,65 @@
----
-title: Helmet Detection
-emoji: 👀
-colorFrom: pink
-colorTo: indigo
-sdk: streamlit
-sdk_version: 1.39.0
-app_file: app.py
-pinned: false
-license: mit
-short_description: helmet detection using YOLOv8 and Nvidia Tritone inference s
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Overview
+This repository provides an ensemble model to combine a YoloV8 model exported from the [Ultralytics](https://github.com/ultralytics/ultralytics) repository with NMS post-processing. The NMS post-processing code contained in [models/postprocess/1/model.py](models/postprocess/1/model.py) is adapted from the [Ultralytics ONNX Example](https://github.com/ultralytics/ultralytics/blob/4b866c97180842b546fe117610869d3c8d69d8ae/examples/YOLOv8-OpenCV-ONNX-Python/main.py).
+
+
+For more information about Triton's Ensemble Models, see their documentation on [Architecture.md](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/architecture.md) and some of their [preprocessing examples](https://github.com/triton-inference-server/python_backend/tree/main/examples/preprocessing).
+
+# Directory Structure
+```
+models/
+    yolov8_onnx/
+        1/
+            model.onnx
+        config.pbtxt
+        
+    postprocess/
+        1/
+            model.py
+        config.pbtxt
+        
+    yolov8_ensemble/
+        1/
+            <Empty Directory>
+        config.pbtxt
+README.md
+main.py
+```
+
+
+# Quick Start
+1. Install [Ultralytics](https://github.com/ultralytics/ultralytics) and TritonClient
+```
+pip install ultralytics==8.0.51 tritonclient[all]==2.31.0
+```
+
+2. Export a model to ONNX format:
+```
+yolo export model=yolov8n.pt format=onnx dynamic=True opset=16
+```
+
+3. Rename the model file to `model.onnx` and place it under the `/models/yolov8_onnx/1` directory (see directory structure above).
+
+4. (Optional): Update the Score and NMS threshold in [models/postprocess/1/model.py](models/postprocess/1/model.py#L59)
+
+5. (Optional): Update the [models/yolov8_ensemble/config.pbtxt](models/yolov8_ensemble/config.pbtxt) file if your input resolution has changed.
+
+6. Build the Docker Container for Triton Inference:
+```
+DOCKER_NAME="yolov8-triton"
+docker build -t $DOCKER_NAME .
+```
+
+6. Run Triton Inference Server:
+```
+DOCKER_NAME="yolov8-triton"
+docker run --gpus all \
+    -it --rm \
+    --net=host \
+    -v ./models:/models \
+    $DOCKER_NAME
+```
+
+7. Run the script with `python main.py`. The overlay image will be written to `output.jpg`.
+
+
+

main.py

@@ -0,0 +1,110 @@
+import numpy as np
+import cv2
+import tritonclient.grpc as grpcclient
+import sys
+import argparse
+
+class_names =['Helmet',"No_helmet","person"]
+  
+def get_triton_client(url: str = 'localhost:8001'):
+    try:
+        keepalive_options = grpcclient.KeepAliveOptions(
+            keepalive_time_ms=2**31 - 1,
+            keepalive_timeout_ms=20000,
+            keepalive_permit_without_calls=False,
+            http2_max_pings_without_data=2
+        )
+        triton_client = grpcclient.InferenceServerClient(
+            url=url,
+            verbose=False,
+            keepalive_options=keepalive_options)
+    except Exception as e:
+        print("channel creation failed: " + str(e))
+        sys.exit()
+    return triton_client
+
+
+def draw_bounding_box(img, class_id, confidence, x, y, x_plus_w, y_plus_h):
+    label = f'{class_names[class_id]}: {confidence:.2f}'
+    color = (255, 0, )
+    cv2.rectangle(img, (x, y), (x_plus_w, y_plus_h), color, 2)
+    cv2.putText(img, label, (x - 10, y - 10),
+                cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
+
+
+def read_image(image_path: str, expected_image_shape) -> np.ndarray:
+    expected_width = expected_image_shape[0]
+    expected_height = expected_image_shape[1]
+    expected_length = min((expected_height, expected_width))
+    original_image: np.ndarray = cv2.imread(image_path)
+    [height, width, _] = original_image.shape
+    length = max((height, width))
+    image = np.zeros((length, length, 3), np.uint8)
+    image[0:height, 0:width] = original_image
+    scale = length / expected_length
+
+    input_image = cv2.resize(image, (expected_width, expected_height))
+    input_image = (input_image / 255.0).astype(np.float32)
+
+    # Channel first
+    input_image = input_image.transpose(2, 0, 1)
+
+    # Expand dimensions
+    input_image = np.expand_dims(input_image, axis=0)
+    return original_image, input_image, scale
+
+
+def run_inference(model_name: str, input_image: np.ndarray,
+                  triton_client: grpcclient.InferenceServerClient):
+    inputs = []
+    outputs = []
+    inputs.append(grpcclient.InferInput('images', input_image.shape, "FP32"))
+    # Initialize the data
+    inputs[0].set_data_from_numpy(input_image)
+
+    outputs.append(grpcclient.InferRequestedOutput('num_detections'))
+    outputs.append(grpcclient.InferRequestedOutput('detection_boxes'))
+    outputs.append(grpcclient.InferRequestedOutput('detection_scores'))
+    outputs.append(grpcclient.InferRequestedOutput('detection_classes'))
+
+    # Test with outputs
+    results = triton_client.infer(model_name=model_name,
+                                  inputs=inputs,
+                                  outputs=outputs)
+
+    num_detections = results.as_numpy('num_detections')
+    detection_boxes = results.as_numpy('detection_boxes')
+    detection_scores = results.as_numpy('detection_scores')
+    detection_classes = results.as_numpy('detection_classes')
+    return num_detections, detection_boxes, detection_scores, detection_classes
+
+
+def main(image_path, model_name, url):
+    triton_client = get_triton_client(url)
+    expected_image_shape = triton_client.get_model_metadata(model_name).inputs[0].shape[-2:]
+    original_image, input_image, scale = read_image(image_path, expected_image_shape)
+    num_detections, detection_boxes, detection_scores, detection_classes = run_inference(
+        model_name, input_image, triton_client)
+    print(detection_classes)
+    print(detection_boxes)
+    for index in range(num_detections[0]):
+        box = detection_boxes[index]
+
+        draw_bounding_box(original_image,
+                          detection_classes[index],
+                          detection_scores[index],
+                          round(box[0] * scale),
+                          round(box[1] * scale),
+                          round((box[0] + box[2]) * scale),
+                          round((box[1] + box[3]) * scale))
+
+    cv2.imwrite('output.jpg', original_image)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--image_path', type=str, default='./assets/Image (47).png')
+    parser.add_argument('--model_name', type=str, default='yolov8_ensemble')
+    parser.add_argument('--url', type=str, default='172.17.0.1:8001')
+    args = parser.parse_args()
+    main(args.image_path, args.model_name, args.url)

models/postprocess/1/model (Copy).py

@@ -0,0 +1,171 @@
+import numpy as np
+import json
+import triton_python_backend_utils as pb_utils
+import cv2
+
+
+class TritonPythonModel:
+    """Your Python model must use the same class name. Every Python model
+    that is created must have "TritonPythonModel" as the class name.
+    """
+
+    def initialize(self, args):
+        """`initialize` is called only once when the model is being loaded.
+        Implementing `initialize` function is optional. This function allows
+        the model to intialize any state associated with this model.
+        Parameters
+        ----------
+        args : dict
+          Both keys and values are strings. The dictionary keys and values are:
+          * model_config: A JSON string containing the model configuration
+          * model_instance_kind: A string containing model instance kind
+          * model_instance_device_id: A string containing model instance device ID
+          * model_repository: Model repository path
+          * model_version: Model version
+          * model_name: Model name
+        """
+
+        # You must parse model_config. JSON string is not parsed here
+        self.model_config = model_config = json.loads(args['model_config'])
+
+        # Get OUTPUT0 configuration
+        num_detections_config = pb_utils.get_output_config_by_name(
+            model_config, "num_detections")
+        detection_boxes_config = pb_utils.get_output_config_by_name(
+            model_config, "detection_boxes")
+
+        detection_scores_config = pb_utils.get_output_config_by_name(
+            model_config, "detection_scores")
+
+        detection_classes_config = pb_utils.get_output_config_by_name(
+            model_config, "detection_classes")
+
+        # Convert Triton types to numpy types
+        self.num_detections_dtype = pb_utils.triton_string_to_numpy(
+            num_detections_config['data_type'])
+
+        # Convert Triton types to numpy types
+        self.detection_boxes_dtype = pb_utils.triton_string_to_numpy(
+            detection_boxes_config['data_type'])
+
+        # Convert Triton types to numpy types
+        self.detection_scores_dtype = pb_utils.triton_string_to_numpy(
+            detection_scores_config['data_type'])
+
+        # Convert Triton types to numpy types
+        self.detection_classes_dtype = pb_utils.triton_string_to_numpy(
+            detection_classes_config['data_type'])
+
+        self.score_threshold = 0.25
+        self.nms_threshold = 0.45
+
+    def execute(self, requests):
+        """`execute` MUST be implemented in every Python model. `execute`
+        function receives a list of pb_utils.InferenceRequest as the only
+        argument. This function is called when an inference request is made
+        for this model. Depending on the batching configuration (e.g. Dynamic
+        Batching) used, `requests` may contain multiple requests. Every
+        Python model, must create one pb_utils.InferenceResponse for every
+        pb_utils.InferenceRequest in `requests`. If there is an error, you can
+        set the error argument when creating a pb_utils.InferenceResponse
+        Parameters
+        ----------
+        requests : list
+          A list of pb_utils.InferenceRequest
+        Returns
+        -------
+        list
+          A list of pb_utils.InferenceResponse. The length of this list must
+          be the same as `requests`
+        """
+
+        num_detections_dtype = self.num_detections_dtype
+        detection_boxes_dtype = self.detection_boxes_dtype
+        detection_scores_dtype = self.detection_scores_dtype
+        detection_classes_dtype = self.detection_classes_dtype
+
+        responses = []
+
+        # Every Python backend must iterate over everyone of the requests
+        # and create a pb_utils.InferenceResponse for each of them.
+        for request in requests:
+            # Get INPUT0
+            in_0 = pb_utils.get_input_tensor_by_name(request, "INPUT_0")
+
+            # Get the output arrays from the results
+            outputs = in_0.as_numpy()
+
+            outputs = np.array([cv2.transpose(outputs[0])])
+            rows = outputs.shape[1]
+
+            boxes = []
+            scores = []
+            class_ids = []
+            for i in range(rows):
+                classes_scores = outputs[0][i][4:]
+                (minScore, maxScore, minClassLoc, (x, maxClassIndex)
+                 ) = cv2.minMaxLoc(classes_scores)
+                if maxScore >= self.score_threshold:
+                    box = [outputs[0][i][0] -
+                           (0.5 *
+                            outputs[0][i][2]), outputs[0][i][1] -
+                           (0.5 *
+                            outputs[0][i][3]), outputs[0][i][2], outputs[0][i][3]]
+                    boxes.append(box)
+                    scores.append(maxScore)
+                    class_ids.append(maxClassIndex)
+
+            result_boxes = cv2.dnn.NMSBoxes(boxes, scores,
+                                            self.score_threshold,
+                                            self.nms_threshold,
+                                            0.5)
+
+            num_detections = 0
+            output_boxes = []
+            output_scores = []
+            output_classids = []
+            for i in range(len(result_boxes)):
+                index = result_boxes[i]
+                box = boxes[index]
+                detection = {
+                    'class_id': class_ids[index],
+                    'confidence': scores[index],
+                    'box': box}
+                output_boxes.append(box)
+                output_scores.append(scores[index])
+                output_classids.append(class_ids[index])
+
+                num_detections += 1
+
+            num_detections = np.array(num_detections)
+            num_detections = pb_utils.Tensor(
+                "num_detections", num_detections.astype(num_detections_dtype))
+
+            detection_boxes = np.array(output_boxes)
+            detection_boxes = pb_utils.Tensor(
+                "detection_boxes", detection_boxes.astype(detection_boxes_dtype))
+
+            detection_scores = np.array(output_scores)
+            detection_scores = pb_utils.Tensor(
+                "detection_scores", detection_scores.astype(detection_scores_dtype))
+            detection_classes = np.array(output_classids)
+            detection_classes = pb_utils.Tensor(
+                "detection_classes",
+                detection_classes.astype(detection_classes_dtype))
+
+            inference_response = pb_utils.InferenceResponse(
+                output_tensors=[
+                    num_detections,
+                    detection_boxes,
+                    detection_scores,
+                    detection_classes])
+            responses.append(inference_response)
+
+        return responses
+
+    def finalize(self):
+        """`finalize` is called only once when the model is being unloaded.
+        Implementing `finalize` function is OPTIONAL. This function allows
+        the model to perform any necessary clean ups before exit.
+        """
+        pass

models/postprocess/1/model.py

@@ -0,0 +1,128 @@
+import numpy as np
+import json
+import triton_python_backend_utils as pb_utils
+import cv2
+
+
+class TritonPythonModel:
+    """Your Python model must use the same class name. Every Python model
+    that is created must have "TritonPythonModel" as the class name.
+    """
+
+    def initialize(self, args):
+        """`initialize` is called only once when the model is being loaded."""
+        self.model_config = model_config = json.loads(args['model_config'])
+
+        # Get OUTPUT0 configuration for Triton output layers
+        num_detections_config = pb_utils.get_output_config_by_name(
+            model_config, "num_detections")
+        detection_boxes_config = pb_utils.get_output_config_by_name(
+            model_config, "detection_boxes")
+        detection_scores_config = pb_utils.get_output_config_by_name(
+            model_config, "detection_scores")
+        detection_classes_config = pb_utils.get_output_config_by_name(
+            model_config, "detection_classes")
+
+        # Convert Triton types to numpy types
+        self.num_detections_dtype = pb_utils.triton_string_to_numpy(
+            num_detections_config['data_type'])
+        self.detection_boxes_dtype = pb_utils.triton_string_to_numpy(
+            detection_boxes_config['data_type'])
+        self.detection_scores_dtype = pb_utils.triton_string_to_numpy(
+            detection_scores_config['data_type'])
+        self.detection_classes_dtype = pb_utils.triton_string_to_numpy(
+            detection_classes_config['data_type'])
+
+        # Thresholds for detection filtering
+        self.score_threshold = 0.25  # Confidence threshold
+        self.nms_threshold = 0.45    # NMS threshold to suppress overlaps
+
+    def execute(self, requests):
+        """The function is executed when inference requests are made."""
+        
+        num_detections_dtype = self.num_detections_dtype
+        detection_boxes_dtype = self.detection_boxes_dtype
+        detection_scores_dtype = self.detection_scores_dtype
+        detection_classes_dtype = self.detection_classes_dtype
+
+        responses = []
+
+        # Process each inference request
+        for request in requests:
+            # Get INPUT0 - input tensor for the model
+            in_0 = pb_utils.get_input_tensor_by_name(request, "INPUT_0")
+
+            # Get the output arrays from the results (assuming batch size of 1)
+            outputs = in_0.as_numpy()
+            outputs = np.array([cv2.transpose(outputs[0])])  # Transpose to match expected format
+            rows = outputs.shape[1]
+
+            boxes = []
+            scores = []
+            class_ids = []
+
+            # Iterate over each detection
+            for i in range(rows):
+                # Extract class scores and determine the best class and its score
+                classes_scores = outputs[0][i][4:]
+                (minScore, maxScore, minClassLoc, (x, maxClassIndex)
+                 ) = cv2.minMaxLoc(classes_scores)
+                
+                if maxScore >= self.score_threshold:  # Filter out low confidence predictions
+                    # YOLO format: (x_center, y_center, width, height)
+                    box = [
+                        outputs[0][i][0] - (0.5 * outputs[0][i][2]),  # x_min
+                        outputs[0][i][1] - (0.5 * outputs[0][i][3]),  # y_min
+                        outputs[0][i][2],  # width
+                        outputs[0][i][3]   # height
+                    ]
+                    boxes.append(box)
+                    scores.append(maxScore)
+                    class_ids.append(maxClassIndex)  # Store the predicted class ID
+
+            # Apply Non-Maximum Suppression (NMS) to remove redundant boxes
+            result_boxes = cv2.dnn.NMSBoxes(boxes, scores, self.score_threshold, self.nms_threshold)
+
+            num_detections = 0
+            output_boxes = []
+            output_scores = []
+            output_classids = []
+
+            # Process the final set of boxes after NMS
+            for i in range(len(result_boxes)):
+                index = result_boxes[i]
+                box = boxes[index]
+                detection = {
+                    'class_id': class_ids[index],    # Store as integer
+                    'confidence': scores[index],     # Confidence score
+                    'box': box                       # Bounding box
+                }
+                output_boxes.append(box)
+                output_scores.append(scores[index])
+                output_classids.append(class_ids[index])
+
+                num_detections += 1
+
+            # Create output tensors for Triton
+            num_detections = np.array([num_detections], dtype=num_detections_dtype)
+            detection_boxes = np.array(output_boxes, dtype=detection_boxes_dtype)
+            detection_scores = np.array(output_scores, dtype=detection_scores_dtype)
+            detection_classes = np.array(output_classids, dtype=detection_classes_dtype)
+
+            # Create the inference response
+            inference_response = pb_utils.InferenceResponse(
+                output_tensors=[
+                    pb_utils.Tensor("num_detections", num_detections),
+                    pb_utils.Tensor("detection_boxes", detection_boxes),
+                    pb_utils.Tensor("detection_scores", detection_scores),
+                    pb_utils.Tensor("detection_classes", detection_classes)
+                ]
+            )
+            responses.append(inference_response)
+
+        return responses
+
+    def finalize(self):
+        """Clean-up function when the model is unloaded."""
+        pass
+

models/postprocess/config.pbtxt

@@ -0,0 +1,35 @@
+name: "postprocess"
+backend: "python"
+max_batch_size: 0 
+    input [
+    {
+        name: "INPUT_0"
+        data_type: TYPE_FP32
+        dims: [-1, -1, -1]
+    }
+]
+ 
+output [
+    {
+      name: "num_detections"
+      data_type: TYPE_INT32
+      dims: [1 ]
+    },
+    {
+      name: "detection_boxes"
+      data_type: TYPE_FP32
+      dims: [1000,4 ]
+    },
+    {
+      name: "detection_scores"
+      data_type: TYPE_FP32 
+      dims: [1000]
+    },
+    {
+      name: "detection_classes"
+      data_type: TYPE_INT32
+      dims: [1000 ]
+    }
+]
+
+instance_group [{ kind: KIND_CPU }]

models/yolov8_ensemble/config.pbtxt

@@ -0,0 +1,72 @@
+name: "yolov8_ensemble"
+platform: "ensemble"
+max_batch_size: 0
+input [
+  {
+    name: "images"
+    data_type: TYPE_FP32
+    dims: [ 1,3,640,640  ]
+  }
+]
+output [
+    {
+      name: "num_detections"
+      data_type: TYPE_INT32
+      dims: [1 ]
+    },
+    {
+      name: "detection_boxes"
+      data_type: TYPE_FP32
+      dims: [1000,4 ]
+    },
+    {
+      name: "detection_scores"
+      data_type: TYPE_FP32 
+      dims: [1000]
+    },
+    {
+      name: "detection_classes"
+      data_type: TYPE_INT32
+      dims: [1000 ]
+    }
+]
+ensemble_scheduling {
+  step [
+    {
+      model_name: "yolov8_onnx"
+      model_version: -1
+      input_map {
+        key: "images"
+        value: "images"
+      }
+      output_map {
+        key: "output0"
+        value: "output0"
+      }
+    },
+    {
+      model_name: "postprocess"
+      model_version: -1
+      input_map {
+        key: "INPUT_0"
+        value: "output0"
+      }
+      output_map {
+        key: "num_detections"
+        value: "num_detections"
+      },
+      output_map {
+        key: "detection_boxes"
+        value: "detection_boxes"
+      },
+      output_map {
+        key: "detection_scores"
+        value: "detection_scores"
+      },
+      output_map {
+        key: "detection_classes"
+        value: "detection_classes"
+      }
+    }
+  ]
+}

models/yolov8_onnx/1/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d145b55c3390438e06bd6510b8eab37b80c508e31a3c4b2783b529a9761a368
+size 174679472

models/yolov8_onnx/config.pbtxt

@@ -0,0 +1,16 @@
+platform: "onnxruntime_onnx"
+max_batch_size: 8
+input [
+{
+  name: "images"
+  data_type: TYPE_FP32
+  dims: [ 3,640,640 ]
+}
+]
+output [
+{
+  name: "output0"
+  data_type: TYPE_FP32
+  dims: [ -1, -1]
+}
+]