Hugging Face's logo

qualcomm
/
YOLO26-Detection

Object Detection
PyTorch
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
5b7dabf
·
verified ·
1 Parent(s): 5af42db

v0.50.2

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.50.2 for changelog.

Files changed (2) hide show
  1. LICENSE +1 -0
  2. README.md +91 -0
LICENSE ADDED
@@ -0,0 +1 @@
 
 
1
+ The license of the original trained model can be found at https://github.com/ultralytics/ultralytics/blob/main/LICENSE.
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: pytorch
3
+ license: other
4
+ tags:
5
+ - real_time
6
+ - android
7
+ pipeline_tag: object-detection
8
+
9
+ ---
10
+
11
+ ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolo26_det/web-assets/model_demo.png)
12
+
13
+ # YOLO26-Detection: Optimized for Qualcomm Devices
14
+
15
+ Ultralytics YOLO26 is a machine learning model that predicts bounding boxes and classes of objects in an image.
16
+
17
+ This is based on the implementation of YOLO26-Detection found [here](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/detect).
18
+ This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/yolo26_det) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
+
20
+ Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
21
+
22
+ ## Getting Started
23
+ Due to licensing restrictions, we cannot distribute pre-exported model assets for this model.
24
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/yolo26_det) Python library to compile and export the model with your own:
25
+ - Custom weights (e.g., fine-tuned checkpoints)
26
+ - Custom input shapes
27
+ - Target device and runtime configurations
28
+
29
+ See our repository for [YOLO26-Detection on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/yolo26_det) for usage instructions.
30
+
31
+
32
+ ## Model Details
33
+
34
+ **Model Type:** Model_use_case.object_detection
35
+
36
+ **Model Stats:**
37
+ - Model checkpoint: YOLO26-N
38
+ - Input resolution: 640x640
39
+ - Number of parameters: 2.4M
40
+ - Model size (float): 9.2 MB
41
+ - Model size (w8a16): 3.2 MB
42
+
43
+ ## Performance Summary
44
+ | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
45
+ |---|---|---|---|---|---|---
46
+ | YOLO26-Detection | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.344 ms | 0 - 81 MB | NPU
47
+ | YOLO26-Detection | ONNX | w8a16 | Snapdragon® X2 Elite | 2.512 ms | 0 - 0 MB | NPU
48
+ | YOLO26-Detection | ONNX | w8a16 | Snapdragon® X Elite | 6.143 ms | 2 - 2 MB | NPU
49
+ | YOLO26-Detection | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.466 ms | 0 - 225 MB | NPU
50
+ | YOLO26-Detection | ONNX | w8a16 | Qualcomm® QCS6490 | 323.555 ms | 99 - 105 MB | CPU
51
+ | YOLO26-Detection | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 5.589 ms | 2 - 7 MB | NPU
52
+ | YOLO26-Detection | ONNX | w8a16 | Qualcomm® QCS9075 | 6.316 ms | 2 - 5 MB | NPU
53
+ | YOLO26-Detection | ONNX | w8a16 | Qualcomm® QCM6690 | 154.87 ms | 101 - 111 MB | CPU
54
+ | YOLO26-Detection | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 2.691 ms | 0 - 75 MB | NPU
55
+ | YOLO26-Detection | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 135.547 ms | 103 - 112 MB | CPU
56
+ | YOLO26-Detection | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.144 ms | 1 - 162 MB | NPU
57
+ | YOLO26-Detection | QNN_DLC | float | Snapdragon® X2 Elite | 2.816 ms | 5 - 5 MB | NPU
58
+ | YOLO26-Detection | QNN_DLC | float | Snapdragon® X Elite | 4.736 ms | 5 - 5 MB | NPU
59
+ | YOLO26-Detection | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.167 ms | 5 - 181 MB | NPU
60
+ | YOLO26-Detection | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 12.913 ms | 1 - 156 MB | NPU
61
+ | YOLO26-Detection | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 4.328 ms | 5 - 6 MB | NPU
62
+ | YOLO26-Detection | QNN_DLC | float | Qualcomm® SA8775P | 5.731 ms | 0 - 157 MB | NPU
63
+ | YOLO26-Detection | QNN_DLC | float | Qualcomm® QCS9075 | 6.153 ms | 7 - 13 MB | NPU
64
+ | YOLO26-Detection | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 8.682 ms | 5 - 197 MB | NPU
65
+ | YOLO26-Detection | QNN_DLC | float | Qualcomm® SA7255P | 12.913 ms | 1 - 156 MB | NPU
66
+ | YOLO26-Detection | QNN_DLC | float | Qualcomm® SA8295P | 9.232 ms | 0 - 168 MB | NPU
67
+ | YOLO26-Detection | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.431 ms | 5 - 165 MB | NPU
68
+ | YOLO26-Detection | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.004 ms | 1 - 183 MB | NPU
69
+ | YOLO26-Detection | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 2.375 ms | 2 - 2 MB | NPU
70
+ | YOLO26-Detection | QNN_DLC | w8a16 | Snapdragon® X Elite | 4.93 ms | 2 - 2 MB | NPU
71
+ | YOLO26-Detection | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.115 ms | 2 - 205 MB | NPU
72
+ | YOLO26-Detection | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 8.251 ms | 1 - 177 MB | NPU
73
+ | YOLO26-Detection | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 4.557 ms | 2 - 4 MB | NPU
74
+ | YOLO26-Detection | QNN_DLC | w8a16 | Qualcomm® SA8775P | 5.24 ms | 1 - 182 MB | NPU
75
+ | YOLO26-Detection | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 5.143 ms | 1 - 5 MB | NPU
76
+ | YOLO26-Detection | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 19.586 ms | 2 - 180 MB | NPU
77
+ | YOLO26-Detection | QNN_DLC | w8a16 | Qualcomm® SA7255P | 8.251 ms | 1 - 177 MB | NPU
78
+ | YOLO26-Detection | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 2.348 ms | 2 - 182 MB | NPU
79
+ | YOLO26-Detection | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 5.084 ms | 2 - 183 MB | NPU
80
+
81
+ ## License
82
+ * The license for the original implementation of YOLO26-Detection can be found
83
+ [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).
84
+
85
+ ## References
86
+ * [Ultralytics YOLO26: NMS-Free Real-Time Object Detection for Edge Devices](https://docs.ultralytics.com/models/yolo26/)
87
+ * [Source Model Implementation](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/detect)
88
+
89
+ ## Community
90
+ * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
91
+ * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).