diff --git a/models/object_detection_yolox/LICENSE b/models/object_detection_yolox/LICENSE
new file mode 100644
index 00000000..1d4dc763
--- /dev/null
+++ b/models/object_detection_yolox/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 (c) 2021-2022 Megvii Inc. All rights reserved.
+
+ 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.
diff --git a/models/object_detection_yolox/README.md b/models/object_detection_yolox/README.md
new file mode 100644
index 00000000..f901bc18
--- /dev/null
+++ b/models/object_detection_yolox/README.md
@@ -0,0 +1,116 @@
+# YOLOX
+
+Nanodet: YOLOX is an anchor-free version of YOLO, with a simpler design but better performance! It aims to bridge the gap between research and industrial communities. YOLOX is a high-performing object detector, an improvement to the existing YOLO series. YOLO series are in constant exploration of techniques to improve the object detection techniques for optimal speed and accuracy trade-off for real-time applications.
+
+Key features of the YOLOX object detector
+- **Anchor-free detectors** significantly reduce the number of design parameters
+- **A decoupled head for classification, regression, and localization** improves the convergence speed
+- **SimOTA advanced label assignment strategy** reduces training time and avoids additional solver hyperparameters
+- **Strong data augmentations like MixUp and Mosiac** to boost YOLOX performance
+
+Note:
+- This version of YoloX: YoloX_s
+
+## Demo
+
+Run the following command to try the demo:
+```shell
+# detect on camera input
+python demo.py
+# detect on an image
+python demo.py --input /path/to/image
+```
+Note:
+- image result saved as "result.jpg"
+
+
+## Results
+
+Here are some of the sample results that were observed using the model (**yolox_s.onnx**),
+
+
+
+
+
+
+
+## Model metrics:
+
+The model is evaluated on [COCO 2017 val](https://cocodataset.org/#download). Results are showed below:
+
+
+Average Precision | Average Recall |
+
+
+| area | IoU | Average Precision(AP) |
+|:-------|:------|:------------------------|
+| all | 0.50:0.95 | 0.405 |
+| all | 0.50 | 0.593 |
+| all | 0.75 | 0.437 |
+| small | 0.50:0.95 | 0.232 |
+| medium | 0.50:0.95 | 0.448 |
+| large | 0.50:0.95 | 0.541 |
+
+ |
+
+ area | IoU | Average Recall(AR) |
+|:-------|:------|:----------------|
+| all | 0.50:0.95 | 0.326 |
+| all | 0.50:0.95 | 0.531 |
+| all | 0.50:0.95 | 0.574 |
+| small | 0.50:0.95 | 0.365 |
+| medium | 0.50:0.95 | 0.634 |
+| large | 0.50:0.95 | 0.724 |
+ |
+
+| class | AP | class | AP | class | AP |
+|:--------------|:-------|:-------------|:-------|:---------------|:-------|
+| person | 54.109 | bicycle | 31.580 | car | 40.447 |
+| motorcycle | 43.477 | airplane | 66.070 | bus | 64.183 |
+| train | 64.483 | truck | 35.110 | boat | 24.681 |
+| traffic light | 25.068 | fire hydrant | 64.382 | stop sign | 65.333 |
+| parking meter | 48.439 | bench | 22.653 | bird | 33.324 |
+| cat | 66.394 | dog | 60.096 | horse | 58.080 |
+| sheep | 49.456 | cow | 53.596 | elephant | 65.574 |
+| bear | 70.541 | zebra | 66.461 | giraffe | 66.780 |
+| backpack | 13.095 | umbrella | 41.614 | handbag | 12.865 |
+| tie | 29.453 | suitcase | 39.089 | frisbee | 61.712 |
+| skis | 21.623 | snowboard | 31.326 | sports ball | 39.820 |
+| kite | 41.410 | baseball bat | 27.311 | baseball glove | 36.661 |
+| skateboard | 49.374 | surfboard | 35.524 | tennis racket | 45.569 |
+| bottle | 37.270 | wine glass | 33.088 | cup | 39.835 |
+| fork | 31.620 | knife | 15.265 | spoon | 14.918 |
+| bowl | 43.251 | banana | 27.904 | apple | 17.630 |
+| sandwich | 32.789 | orange | 29.388 | broccoli | 23.187 |
+| carrot | 23.114 | hot dog | 33.716 | pizza | 52.541 |
+| donut | 47.980 | cake | 36.160 | chair | 29.707 |
+| couch | 46.175 | potted plant | 24.781 | bed | 44.323 |
+| dining table | 30.022 | toilet | 64.237 | tv | 57.301 |
+| laptop | 58.362 | mouse | 57.774 | remote | 24.271 |
+| keyboard | 48.020 | cell phone | 32.376 | microwave | 57.220 |
+| oven | 36.168 | toaster | 28.735 | sink | 38.159 |
+| refrigerator | 52.876 | book | 15.030 | clock | 48.622 |
+| vase | 37.013 | scissors | 26.307 | teddy bear | 45.676 |
+| hair drier | 7.255 | toothbrush | 19.374 | | |
+
+## License
+
+All files in this directory are licensed under [Apache 2.0 License](./LICENSE).
+
+#### Contributor Details
+
+- Google Summer of Code'22
+- Contributor: Sri Siddarth Chakaravarthy
+- Github Profile: https://github.com/Sidd1609
+- Organisation: OpenCV
+- Project: Lightweight object detection models using OpenCV
+
+## Reference
+
+- YOLOX article: https://arxiv.org/abs/2107.08430
+- YOLOX weight and scripts for training: https://github.com/Megvii-BaseDetection/YOLOX
+- YOLOX blog: https://arshren.medium.com/yolox-new-improved-yolo-d430c0e4cf20
+- YOLOX-lite: https://github.com/TexasInstruments/edgeai-yolox
diff --git a/models/object_detection_yolox/YoloX.py b/models/object_detection_yolox/YoloX.py
new file mode 100644
index 00000000..615477e0
--- /dev/null
+++ b/models/object_detection_yolox/YoloX.py
@@ -0,0 +1,93 @@
+import numpy as np
+import cv2
+
+class YoloX:
+ def __init__(self, modelPath, confThreshold=0.35, nmsThreshold=0.5, objThreshold=0.5, backendId=0, targetId=0):
+ self.num_classes = 80
+ self.net = cv2.dnn.readNet(modelPath)
+ self.input_size = (640, 640)
+ self.mean = np.array([0.485, 0.456, 0.406], dtype=np.float32).reshape(1, 1, 3)
+ self.std = np.array([0.229, 0.224, 0.225], dtype=np.float32).reshape(1, 1, 3)
+ self.strides = [8, 16, 32]
+ self.confThreshold = confThreshold
+ self.nmsThreshold = nmsThreshold
+ self.objThreshold = objThreshold
+ self.backendId = backendId
+ self.targetId = targetId
+ self.net.setPreferableBackend(self.backendId)
+ self.net.setPreferableTarget(self.targetId)
+
+ @property
+ def name(self):
+ return self.__class__.__name__
+
+ def setBackend(self, backenId):
+ self.backendId = backendId
+ self.net.setPreferableBackend(self.backendId)
+
+ def setTarget(self, targetId):
+ self.targetId = targetId
+ self.net.setPreferableTarget(self.targetId)
+
+ def preprocess(self, img):
+ blob = np.transpose(img, (2, 0, 1))
+ return blob[np.newaxis, :, :, :]
+
+ def infer(self, srcimg):
+ input_blob = self.preprocess(srcimg)
+
+ self.net.setInput(input_blob)
+ outs = self.net.forward(self.net.getUnconnectedOutLayersNames())
+
+ predictions = self.postprocess(outs[0])
+ return predictions
+
+ def postprocess(self, outputs):
+ grids = []
+ expanded_strides = []
+ hsizes = [self.input_size[0] // stride for stride in self.strides]
+ wsizes = [self.input_size[1] // stride for stride in self.strides]
+
+ for hsize, wsize, stride in zip(hsizes, wsizes, self.strides):
+ xv, yv = np.meshgrid(np.arange(hsize), np.arange(wsize))
+ grid = np.stack((xv, yv), 2).reshape(1, -1, 2)
+ grids.append(grid)
+ shape = grid.shape[:2]
+ expanded_strides.append(np.full((*shape, 1), stride))
+
+ grids = np.concatenate(grids, 1)
+ expanded_strides = np.concatenate(expanded_strides, 1)
+ outputs[..., :2] = (outputs[..., :2] + grids) * expanded_strides
+ outputs[..., 2:4] = np.exp(outputs[..., 2:4]) * expanded_strides
+
+ predictions = outputs[0]
+
+ boxes = predictions[:, :4]
+ scores = predictions[:, 4:5] * predictions[:, 5:]
+
+ boxes_xyxy = np.ones_like(boxes)
+ boxes_xyxy[:, 0] = boxes[:, 0] - boxes[:, 2] / 2.
+ boxes_xyxy[:, 1] = boxes[:, 1] - boxes[:, 3] / 2.
+ boxes_xyxy[:, 2] = boxes[:, 0] + boxes[:, 2] / 2.
+ boxes_xyxy[:, 3] = boxes[:, 1] + boxes[:, 3] / 2.
+
+ # multi-class nms
+ final_dets = []
+ for cls_ind in range(scores.shape[1]):
+ cls_scores = scores[:, cls_ind]
+ valid_score_mask = cls_scores > self.confThreshold
+ if valid_score_mask.sum() == 0:
+ continue
+ else:
+ # call nms
+ indices = cv2.dnn.NMSBoxes(boxes_xyxy.tolist(), cls_scores.tolist(), self.confThreshold, self.nmsThreshold)
+
+ classids_ = np.ones((len(indices), 1)) * cls_ind
+ final_dets.append(
+ np.concatenate([boxes_xyxy[indices], cls_scores[indices, None], classids_], axis=1)
+ )
+
+ if len(final_dets) == 0:
+ return np.array([])
+
+ return np.concatenate(final_dets, 0)
diff --git a/models/object_detection_yolox/demo.py b/models/object_detection_yolox/demo.py
new file mode 100644
index 00000000..ed31f1f2
--- /dev/null
+++ b/models/object_detection_yolox/demo.py
@@ -0,0 +1,146 @@
+import numpy as np
+import cv2
+import argparse
+
+from yolox import YoloX
+
+def str2bool(v):
+ if v.lower() in ['on', 'yes', 'true', 'y', 't']:
+ return True
+ elif v.lower() in ['off', 'no', 'false', 'n', 'f']:
+ return False
+ else:
+ raise NotImplementedError
+
+backends = [cv2.dnn.DNN_BACKEND_OPENCV, cv2.dnn.DNN_BACKEND_CUDA]
+targets = [cv2.dnn.DNN_TARGET_CPU, cv2.dnn.DNN_TARGET_CUDA, cv2.dnn.DNN_TARGET_CUDA_FP16]
+help_msg_backends = "Choose one of the computation backends: {:d}: OpenCV implementation (default); {:d}: CUDA"
+help_msg_targets = "Chose one of the target computation devices: {:d}: CPU (default); {:d}: CUDA; {:d}: CUDA fp16"
+
+try:
+ backends += [cv2.dnn.DNN_BACKEND_TIMVX]
+ targets += [cv2.dnn.DNN_TARGET_NPU]
+ help_msg_backends += "; {:d}: TIMVX"
+ help_msg_targets += "; {:d}: NPU"
+except:
+ print('This version of OpenCV does not support TIM-VX and NPU. Visit https://github.com/opencv/opencv/wiki/TIM-VX-Backend-For-Running-OpenCV-On-NPU for more information.')
+
+classes = ('person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
+ 'train', 'truck', 'boat', 'traffic light', 'fire hydrant',
+ 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog',
+ 'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe',
+ 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
+ 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat',
+ 'baseball glove', 'skateboard', 'surfboard', 'tennis racket',
+ 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl',
+ 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot',
+ 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
+ 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop',
+ 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave',
+ 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock',
+ 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush')
+
+def letterbox(srcimg, target_size=(640, 640)):
+ padded_img = np.ones((target_size[0], target_size[1], 3)) * 114.0
+ ratio = min(target_size[0] / srcimg.shape[0], target_size[1] / srcimg.shape[1])
+ resized_img = cv2.resize(
+ srcimg, (int(srcimg.shape[1] * ratio), int(srcimg.shape[0] * ratio)), interpolation=cv2.INTER_LINEAR
+ ).astype(np.float32)
+ padded_img[: int(srcimg.shape[0] * ratio), : int(srcimg.shape[1] * ratio)] = resized_img
+
+ return padded_img, ratio
+
+def unletterbox(bbox, letterbox_scale):
+ return bbox / letterbox_scale
+
+def vis(dets, srcimg, letterbox_scale, fps=None):
+ res_img = srcimg.copy()
+
+ if fps is not None:
+ fps_label = "FPS: %.2f" % fps
+ cv2.putText(res_img, fps_label, (10, 25), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
+
+ for det in dets:
+ box = unletterbox(det[:4], letterbox_scale).astype(np.int32)
+ score = det[-2]
+ cls_id = int(det[-1])
+
+ x0, y0, x1, y1 = box
+
+ text = '{}:{:.1f}%'.format(classes[cls_id], score * 100)
+ font = cv2.FONT_HERSHEY_SIMPLEX
+ txt_size = cv2.getTextSize(text, font, 0.4, 1)[0]
+ cv2.rectangle(res_img, (x0, y0), (x1, y1), (0, 255, 0), 2)
+ cv2.rectangle(res_img, (x0, y0 + 1), (x0 + txt_size[0] + 1, y0 + int(1.5 * txt_size[1])), (255, 255, 255), -1)
+ cv2.putText(res_img, text, (x0, y0 + txt_size[1]), font, 0.4, (0, 0, 0), thickness=1)
+
+ return res_img
+
+if __name__=='__main__':
+ parser = argparse.ArgumentParser(description='Nanodet inference using OpenCV an contribution by Sri Siddarth Chakaravarthy part of GSOC_2022')
+ parser.add_argument('--input', '-i', type=str, help='Path to the input image. Omit for using default camera.')
+ parser.add_argument('--model', '-m', type=str, default='object_detection_yolox_2022nov.onnx', help="Path to the model")
+ parser.add_argument('--backend', '-b', type=int, default=backends[0], help=help_msg_backends.format(*backends))
+ parser.add_argument('--target', '-t', type=int, default=targets[0], help=help_msg_targets.format(*targets))
+ parser.add_argument('--confidence', default=0.5, type=float, help='Class confidence')
+ parser.add_argument('--nms', default=0.5, type=float, help='Enter nms IOU threshold')
+ parser.add_argument('--obj', default=0.5, type=float, help='Enter object threshold')
+ parser.add_argument('--save', '-s', type=str2bool, default=False, help='Set true to save results. This flag is invalid when using camera.')
+ parser.add_argument('--vis', '-v', type=str2bool, default=True, help='Set true to open a window for result visualization. This flag is invalid when using camera.')
+ args = parser.parse_args()
+
+ model_net = YoloX(modelPath= args.model,
+ confThreshold=args.confidence,
+ nmsThreshold=args.nms,
+ objThreshold=args.obj,
+ backendId=args.backend,
+ targetId=args.target)
+
+ tm = cv2.TickMeter()
+ tm.reset()
+ if args.input is not None:
+ image = cv2.imread(args.input)
+ input_blob = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+ input_blob, letterbox_scale = letterbox(input_blob)
+
+ # Inference
+ tm.start()
+ preds = model_net.infer(input_blob)
+ tm.stop()
+ print("Inference time: {:.2f} ms".format(tm.getTimeMilli()))
+
+ img = vis(preds, image, letterbox_scale)
+
+ if args.save:
+ print('Resutls saved to result.jpg\n')
+ cv2.imwrite('result.jpg', img)
+
+ if args.vis:
+ cv2.namedWindow(args.input, cv2.WINDOW_AUTOSIZE)
+ cv2.imshow(args.input, img)
+ cv2.waitKey(0)
+
+ else:
+ print("Press any key to stop video capture")
+ deviceId = 0
+ cap = cv2.VideoCapture(deviceId)
+
+ while cv2.waitKey(1) < 0:
+ hasFrame, frame = cap.read()
+ if not hasFrame:
+ print('No frames grabbed!')
+ break
+
+ input_blob = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+ input_blob, letterbox_scale = letterbox(input_blob)
+
+ # Inference
+ tm.start()
+ preds = model_net.infer(input_blob)
+ tm.stop()
+
+ img = vis(preds, frame, letterbox_scale, fps=tm.getFPS())
+
+ cv2.imshow("YoloX Demo", img)
+
+ tm.reset()
diff --git a/models/object_detection_yolox/object_detection_yolox_2022nov.onnx b/models/object_detection_yolox/object_detection_yolox_2022nov.onnx
new file mode 100644
index 00000000..0a22cdd5
--- /dev/null
+++ b/models/object_detection_yolox/object_detection_yolox_2022nov.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5c2d13e59ae883e6af3b45daea64af4833a4951c92d116ec270d9ddbe998063
+size 35858002
diff --git a/models/object_detection_yolox/object_detection_yolox_2022nov_int8.onnx b/models/object_detection_yolox/object_detection_yolox_2022nov_int8.onnx
new file mode 100644
index 00000000..af996081
--- /dev/null
+++ b/models/object_detection_yolox/object_detection_yolox_2022nov_int8.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01a3b0f400b30bc1e45230e991b2e499ab42622485a330021947333fbaf03935
+size 9079452
diff --git a/models/object_detection_yolox/samples/1_res.jpg b/models/object_detection_yolox/samples/1_res.jpg
new file mode 100644
index 00000000..c56e9ff5
Binary files /dev/null and b/models/object_detection_yolox/samples/1_res.jpg differ
diff --git a/models/object_detection_yolox/samples/2_res.jpg b/models/object_detection_yolox/samples/2_res.jpg
new file mode 100644
index 00000000..7eb30168
Binary files /dev/null and b/models/object_detection_yolox/samples/2_res.jpg differ
diff --git a/models/object_detection_yolox/samples/3_res.jpg b/models/object_detection_yolox/samples/3_res.jpg
new file mode 100644
index 00000000..5e94e369
Binary files /dev/null and b/models/object_detection_yolox/samples/3_res.jpg differ