Hugging Face's logo

qualcomm
/
YOLOv11-Detection-Quantized

Object Detection
PyTorch
real_time
quantized
android
Model card Files Community
qaihm-bot commited on
Commit
f9ead1e
·
verified ·
1 Parent(s): b32e246

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +108 -0
README.md ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: pytorch
3
+ license: agpl-3.0
4
+ tags:
5
+ - real_time
6
+ - quantized
7
+ - android
8
+ pipeline_tag: object-detection
9
+
10
+ ---
11
+
12
+ ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolov11_det_quantized/web-assets/model_demo.png)
13
+
14
+ # YOLOv11-Detection-Quantized: Optimized for Mobile Deployment
15
+ ## Quantized real-time object detection optimized for mobile and edge by Ultralytics
16
+
17
+
18
+ Ultralytics YOLOv11 is a machine learning model that predicts bounding boxes and classes of objects in an image. This model is post-training quantized to int8 using samples from the COCO dataset.
19
+
20
+ This model is an implementation of YOLOv11-Detection-Quantized found [here](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/detect).
21
+
22
+
23
+ More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/yolov11_det_quantized).
24
+
25
+ ### Model Details
26
+
27
+ - **Model Type:** Object detection
28
+ - **Model Stats:**
29
+ - Model checkpoint: YOLOv11-N
30
+ - Input resolution: 640x640
31
+ - Number of parameters: 2.64M
32
+ - Model size: 2.83 MB
33
+
34
+ | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
35
+ |---|---|---|---|---|---|---|---|---|
36
+ | YOLOv11-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 1.833 ms | 0 - 12 MB | INT8 | NPU | -- |
37
+ | YOLOv11-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.822 ms | 1 - 4 MB | INT8 | NPU | -- |
38
+ | YOLOv11-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 10.152 ms | 0 - 20 MB | INT8 | NPU | -- |
39
+ | YOLOv11-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 1.202 ms | 0 - 34 MB | INT8 | NPU | -- |
40
+ | YOLOv11-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.223 ms | 1 - 20 MB | INT8 | NPU | -- |
41
+ | YOLOv11-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 7.445 ms | 1 - 64 MB | INT8 | NPU | -- |
42
+ | YOLOv11-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.924 ms | 0 - 33 MB | INT8 | NPU | -- |
43
+ | YOLOv11-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.24 ms | 1 - 30 MB | INT8 | NPU | -- |
44
+ | YOLOv11-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 7.109 ms | 2 - 63 MB | INT8 | NPU | -- |
45
+ | YOLOv11-Detection-Quantized | SA7255P ADP | SA7255P | TFLITE | 9.079 ms | 0 - 22 MB | INT8 | NPU | -- |
46
+ | YOLOv11-Detection-Quantized | SA7255P ADP | SA7255P | QNN | 8.966 ms | 1 - 9 MB | INT8 | NPU | -- |
47
+ | YOLOv11-Detection-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 1.832 ms | 0 - 13 MB | INT8 | NPU | -- |
48
+ | YOLOv11-Detection-Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.817 ms | 1 - 4 MB | INT8 | NPU | -- |
49
+ | YOLOv11-Detection-Quantized | SA8295P ADP | SA8295P | TFLITE | 2.662 ms | 0 - 26 MB | INT8 | NPU | -- |
50
+ | YOLOv11-Detection-Quantized | SA8295P ADP | SA8295P | QNN | 2.607 ms | 1 - 16 MB | INT8 | NPU | -- |
51
+ | YOLOv11-Detection-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 1.819 ms | 0 - 10 MB | INT8 | NPU | -- |
52
+ | YOLOv11-Detection-Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 1.823 ms | 1 - 4 MB | INT8 | NPU | -- |
53
+ | YOLOv11-Detection-Quantized | SA8775P ADP | SA8775P | TFLITE | 2.715 ms | 0 - 22 MB | INT8 | NPU | -- |
54
+ | YOLOv11-Detection-Quantized | SA8775P ADP | SA8775P | QNN | 2.688 ms | 1 - 11 MB | INT8 | NPU | -- |
55
+ | YOLOv11-Detection-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 4.081 ms | 0 - 28 MB | INT8 | NPU | -- |
56
+ | YOLOv11-Detection-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 5.937 ms | 1 - 13 MB | INT8 | NPU | -- |
57
+ | YOLOv11-Detection-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 66.03 ms | 1 - 11 MB | INT8 | NPU | -- |
58
+ | YOLOv11-Detection-Quantized | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 9.079 ms | 0 - 22 MB | INT8 | NPU | -- |
59
+ | YOLOv11-Detection-Quantized | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 8.966 ms | 1 - 9 MB | INT8 | NPU | -- |
60
+ | YOLOv11-Detection-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 1.821 ms | 0 - 8 MB | INT8 | NPU | -- |
61
+ | YOLOv11-Detection-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 1.804 ms | 1 - 4 MB | INT8 | NPU | -- |
62
+ | YOLOv11-Detection-Quantized | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 2.715 ms | 0 - 22 MB | INT8 | NPU | -- |
63
+ | YOLOv11-Detection-Quantized | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 2.688 ms | 1 - 11 MB | INT8 | NPU | -- |
64
+ | YOLOv11-Detection-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.98 ms | 0 - 30 MB | INT8 | NPU | -- |
65
+ | YOLOv11-Detection-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 2.242 ms | 1 - 30 MB | INT8 | NPU | -- |
66
+ | YOLOv11-Detection-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 2.097 ms | 1 - 1 MB | INT8 | NPU | -- |
67
+ | YOLOv11-Detection-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 10.967 ms | 2 - 2 MB | INT8 | NPU | -- |
68
+
69
+
70
+
71
+
72
+ ## License
73
+ * The license for the original implementation of YOLOv11-Detection-Quantized can be found
74
+ [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).
75
+ * The license for the compiled assets for on-device deployment can be found [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE)
76
+
77
+
78
+
79
+ ## References
80
+ * [Ultralytics YOLOv8 Docs: Object Detection](https://docs.ultralytics.com/tasks/detect/)
81
+ * [Source Model Implementation](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/detect)
82
+
83
+
84
+
85
+ ## Community
86
+ * Join [our AI Hub Slack community](https://qualcomm-ai-hub.slack.com/join/shared_invite/zt-2d5zsmas3-Sj0Q9TzslueCjS31eXG2UA#/shared-invite/email) to collaborate, post questions and learn more about on-device AI.
87
+ * For questions or feedback please [reach out to us](mailto:[email protected]).
88
+
89
+ ## Usage and Limitations
90
+
91
+ Model may not be used for or in connection with any of the following applications:
92
+
93
+ - Accessing essential private and public services and benefits;
94
+ - Administration of justice and democratic processes;
95
+ - Assessing or recognizing the emotional state of a person;
96
+ - Biometric and biometrics-based systems, including categorization of persons based on sensitive characteristics;
97
+ - Education and vocational training;
98
+ - Employment and workers management;
99
+ - Exploitation of the vulnerabilities of persons resulting in harmful behavior;
100
+ - General purpose social scoring;
101
+ - Law enforcement;
102
+ - Management and operation of critical infrastructure;
103
+ - Migration, asylum and border control management;
104
+ - Predictive policing;
105
+ - Real-time remote biometric identification in public spaces;
106
+ - Recommender systems of social media platforms;
107
+ - Scraping of facial images (from the internet or otherwise); and/or
108
+ - Subliminal manipulation