Hugging Face's logo

qualcomm
/
YOLOE-Segmentation

Image Segmentation
PyTorch
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
fcf7722
·
verified ·
1 Parent(s): 7c3078b

v0.56.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.56.0 for changelog.

Files changed (2) hide show
  1. LICENSE +1 -0
  2. README.md +113 -0
LICENSE ADDED
@@ -0,0 +1 @@
 
 
1
+ The license of the original trained model can be found at https://github.com/THU-MIG/yoloe/blob/main/LICENSE.
README.md ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: pytorch
3
+ license: other
4
+ tags:
5
+ - real_time
6
+ - android
7
+ pipeline_tag: image-segmentation
8
+
9
+ ---
10
+
11
+ ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yoloe_seg/web-assets/model_demo.png)
12
+
13
+ # YOLOE-Segmentation: Optimized for Qualcomm Devices
14
+
15
+ Ultralytics YOLOE is a machine learning model that predicts bounding boxes, segmentation masks and classes of objects in an image.
16
+
17
+ This is based on the implementation of YOLOE-Segmentation found [here](https://github.com/THU-MIG/yoloe).
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/yoloe_seg) 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/yoloe_seg) 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 [YOLOE-Segmentation on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/yoloe_seg) for usage instructions.
30
+
31
+
32
+ ## Model Details
33
+
34
+ **Model Type:** Model_use_case.semantic_segmentation
35
+
36
+ **Model Stats:**
37
+ - Model checkpoint: YOLOE-v8L-SEG
38
+ - Input resolution: 640x640
39
+ - Number of parameters: 53.47M
40
+ - Model size (float): 103 MB
41
+
42
+ ## Performance Summary
43
+ | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
44
+ |---|---|---|---|---|---|---
45
+ | YOLOE-Segmentation | ONNX | float | Snapdragon® X2 Elite | 15.676 ms | 176 - 176 MB | NPU
46
+ | YOLOE-Segmentation | ONNX | float | Snapdragon® X Elite | 31.024 ms | 145 - 145 MB | NPU
47
+ | YOLOE-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 24.169 ms | 17 - 289 MB | NPU
48
+ | YOLOE-Segmentation | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 68.04 ms | 17 - 335 MB | NPU
49
+ | YOLOE-Segmentation | ONNX | float | Qualcomm® QCS8550 (Proxy) | 30.679 ms | 0 - 95 MB | NPU
50
+ | YOLOE-Segmentation | ONNX | float | Qualcomm® QCS8450 | 68.04 ms | 17 - 335 MB | NPU
51
+ | YOLOE-Segmentation | ONNX | float | Snapdragon® 8 Elite Mobile | 18.194 ms | 12 - 232 MB | NPU
52
+ | YOLOE-Segmentation | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 12.031 ms | 13 - 242 MB | NPU
53
+ | YOLOE-Segmentation | ONNX | float | Qualcomm® QCS9075 | 48.175 ms | 17 - 62 MB | NPU
54
+ | YOLOE-Segmentation | ONNX | float | Qualcomm® QCS8750 | 18.194 ms | 12 - 232 MB | NPU
55
+ | YOLOE-Segmentation | ONNX | float | Qualcomm® QCS7181 | 31.024 ms | 145 - 145 MB | NPU
56
+ | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 15.499 ms | 5 - 5 MB | NPU
57
+ | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 29.182 ms | 5 - 5 MB | NPU
58
+ | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 21.749 ms | 5 - 269 MB | NPU
59
+ | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 62.519 ms | 5 - 315 MB | NPU
60
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® QCS8275 | 178.782 ms | 1 - 209 MB | NPU
61
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 28.102 ms | 5 - 7 MB | NPU
62
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 | 62.519 ms | 5 - 315 MB | NPU
63
+ | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 17.151 ms | 5 - 219 MB | NPU
64
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 178.782 ms | 1 - 209 MB | NPU
65
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 49.982 ms | 0 - 248 MB | NPU
66
+ | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 11.406 ms | 4 - 216 MB | NPU
67
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® QCS9075 | 46.076 ms | 5 - 15 MB | NPU
68
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® QCS8750 | 17.151 ms | 5 - 219 MB | NPU
69
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® QCS7181 | 29.182 ms | 5 - 5 MB | NPU
70
+ | YOLOE-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 21.128 ms | 34 - 379 MB | NPU
71
+ | YOLOE-Segmentation | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 62.578 ms | 0 - 391 MB | NPU
72
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® QCS8275 | 177.45 ms | 5 - 237 MB | NPU
73
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 27.334 ms | 0 - 140 MB | NPU
74
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® SA8775P | 1634.277 ms | 50 - 61 MB | CPU
75
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® SA8650P | 1634.277 ms | 50 - 61 MB | CPU
76
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® SA8255P | 1634.277 ms | 50 - 61 MB | CPU
77
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® QCS8450 | 62.578 ms | 0 - 391 MB | NPU
78
+ | YOLOE-Segmentation | TFLITE | float | Snapdragon® 8 Elite Mobile | 16.323 ms | 4 - 246 MB | NPU
79
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® SA7255P | 177.45 ms | 5 - 237 MB | NPU
80
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® SA8295P | 48.524 ms | 5 - 277 MB | NPU
81
+ | YOLOE-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 10.924 ms | 3 - 245 MB | NPU
82
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® QCS9075 | 44.982 ms | 4 - 106 MB | NPU
83
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® QCS8750 | 16.323 ms | 4 - 246 MB | NPU
84
+ | YOLOE-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 6.277 ms | 1 - 306 MB | NPU
85
+ | YOLOE-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 12.967 ms | 1 - 305 MB | NPU
86
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCS6490 | 34.017 ms | 1 - 51 MB | NPU
87
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8275 | 27.001 ms | 1 - 229 MB | NPU
88
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 8.098 ms | 1 - 31 MB | NPU
89
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® SA8775P | 482.445 ms | 13 - 25 MB | CPU
90
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® SA8650P | 482.445 ms | 13 - 25 MB | CPU
91
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® SA8255P | 482.445 ms | 13 - 25 MB | CPU
92
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8450 | 12.967 ms | 1 - 305 MB | NPU
93
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® SA7255P | 27.001 ms | 1 - 229 MB | NPU
94
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCM6690 | 163.707 ms | 1 - 249 MB | NPU
95
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® SA8295P | 14.517 ms | 1 - 233 MB | NPU
96
+ | YOLOE-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.443 ms | 1 - 244 MB | NPU
97
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCS9075 | 9.095 ms | 0 - 49 MB | NPU
98
+ | YOLOE-Segmentation | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 13.691 ms | 0 - 228 MB | NPU
99
+ | YOLOE-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 5.001 ms | 1 - 232 MB | NPU
100
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCS7790 | 13.691 ms | 0 - 228 MB | NPU
101
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8750 | 5.001 ms | 1 - 232 MB | NPU
102
+
103
+ ## License
104
+ * The license for the original implementation of YOLOE-Segmentation can be found
105
+ [here](https://github.com/THU-MIG/yoloe/blob/main/LICENSE).
106
+
107
+ ## References
108
+ * [YOLOE: Real-Time Seeing Anything](https://arxiv.org/abs/2503.07465)
109
+ * [Source Model Implementation](https://github.com/THU-MIG/yoloe)
110
+
111
+ ## Community
112
+ * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
113
+ * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).