Hugging Face's logo

qualcomm
/
OSNet

PyTorch
backbone
real_time
android
video-object-tracking
Model card Files
xet
 Community
qaihm-bot commited on
Commit
c0d592f
·
verified ·
1 Parent(s): d2ea8af

v0.61.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.61.0 for changelog.

Files changed (3) hide show
  1. LICENSE +1 -0
  2. README.md +163 -0
  3. release_assets.json +44 -0
LICENSE ADDED
@@ -0,0 +1 @@
 
 
1
+ The license of the original trained model can be found at https://github.com/KaiyangZhou/deep-person-reid/blob/master/LICENSE.
README.md ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: pytorch
3
+ license: mit
4
+ tags:
5
+ - backbone
6
+ - real_time
7
+ - android
8
+ pipeline_tag: video-object-tracking
9
+
10
+ ---
11
+
12
+ ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/osnet/web-assets/model_demo.png)
13
+
14
+ # OSNet: Optimized for Qualcomm Devices
15
+
16
+ OSNet is a compact convolutional architecture for person re-identification. It extracts discriminative embeddings that can be compared with cosine similarity for person matching across camera views.
17
+
18
+ This is based on the implementation of OSNet found [here](https://github.com/KaiyangZhou/deep-person-reid).
19
+ 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/v0.61.0/src/qai_hub_models/models/osnet) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
20
+
21
+ 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.
22
+
23
+ ## Getting Started
24
+ There are two ways to deploy this model on your device:
25
+
26
+ ### Option 1: Download Pre-Exported Models
27
+
28
+ Below are pre-exported model assets ready for deployment.
29
+
30
+ | Runtime | Precision | Chipset | SDK Versions | Download |
31
+ |---|---|---|---|---|
32
+ | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/osnet/releases/v0.61.0/osnet-onnx-float.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/osnet/releases/v0.61.0/osnet-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/osnet/releases/v0.61.0/osnet-qnn_dlc-w8a8.zip)
35
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/osnet/releases/v0.61.0/osnet-tflite-float.zip)
36
+ | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/osnet/releases/v0.61.0/osnet-tflite-w8a8.zip)
37
+
38
+ For more device-specific assets and performance metrics, visit **[OSNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/osnet)**.
39
+
40
+
41
+ ### Option 2: Export with Custom Configurations
42
+
43
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/osnet) Python library to compile and export the model with your own:
44
+ - Custom weights (e.g., fine-tuned checkpoints)
45
+ - Custom input shapes
46
+ - Target device and runtime configurations
47
+
48
+ This option is ideal if you need to customize the model beyond the default configuration provided here.
49
+
50
+ See our repository for [OSNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/osnet) for usage instructions.
51
+
52
+ ## Model Details
53
+
54
+ **Model Type:** Model_use_case.video_object_tracking
55
+
56
+ **Model Stats:**
57
+ - Input resolution: 256x128
58
+ - Model checkpoint: osnet_x1_0_market_256x128_amsgrad_ep150_stp60_lr0.0015_b64_fb10_softmax_labelsmooth_flip.pth
59
+ - Model size (float): 8.69 MB
60
+ - Model size (w8a8): 3.57 MB
61
+ - Number of parameters: 2.68M
62
+
63
+ ## Performance Summary
64
+ | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
+ |---|---|---|---|---|---|---
66
+ | OSNet | ONNX | float | Snapdragon® X2 Elite | 0.497 ms | 1 - 1 MB | NPU
67
+ | OSNet | ONNX | float | Snapdragon® X Elite | 0.934 ms | 0 - 0 MB | NPU
68
+ | OSNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.617 ms | 0 - 71 MB | NPU
69
+ | OSNet | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 1.598 ms | 0 - 68 MB | NPU
70
+ | OSNet | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 1.406 ms | 0 - 4 MB | NPU
71
+ | OSNet | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.89 ms | 0 - 95 MB | NPU
72
+ | OSNet | ONNX | float | Qualcomm® QCS8450 | 1.598 ms | 0 - 68 MB | NPU
73
+ | OSNet | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 1.395 ms | 0 - 3 MB | NPU
74
+ | OSNet | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 0.934 ms | 0 - 0 MB | NPU
75
+ | OSNet | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.49 ms | 0 - 53 MB | NPU
76
+ | OSNet | ONNX | float | Snapdragon® 8 Elite Mobile | 0.49 ms | 0 - 53 MB | NPU
77
+ | OSNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.456 ms | 0 - 54 MB | NPU
78
+ | OSNet | QNN_DLC | float | Snapdragon® X2 Elite | 0.643 ms | 0 - 0 MB | NPU
79
+ | OSNet | QNN_DLC | float | Snapdragon® X Elite | 1.243 ms | 0 - 0 MB | NPU
80
+ | OSNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.705 ms | 0 - 58 MB | NPU
81
+ | OSNet | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 2.022 ms | 0 - 62 MB | NPU
82
+ | OSNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 1.441 ms | 0 - 3 MB | NPU
83
+ | OSNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 4.564 ms | 0 - 43 MB | NPU
84
+ | OSNet | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.052 ms | 0 - 10 MB | NPU
85
+ | OSNet | QNN_DLC | float | Qualcomm® SA8775P | 1.68 ms | 0 - 47 MB | NPU
86
+ | OSNet | QNN_DLC | float | Qualcomm® SA8650P | 1.68 ms | 0 - 47 MB | NPU
87
+ | OSNet | QNN_DLC | float | Qualcomm® SA8255P | 1.68 ms | 0 - 47 MB | NPU
88
+ | OSNet | QNN_DLC | float | Qualcomm® QCS8450 | 2.022 ms | 0 - 62 MB | NPU
89
+ | OSNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.482 ms | 0 - 2 MB | NPU
90
+ | OSNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.243 ms | 0 - 0 MB | NPU
91
+ | OSNet | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.533 ms | 0 - 49 MB | NPU
92
+ | OSNet | QNN_DLC | float | Qualcomm® SA7255P | 4.564 ms | 0 - 43 MB | NPU
93
+ | OSNet | QNN_DLC | float | Qualcomm® SA8295P | 2.187 ms | 0 - 40 MB | NPU
94
+ | OSNet | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 0.533 ms | 0 - 49 MB | NPU
95
+ | OSNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.428 ms | 0 - 47 MB | NPU
96
+ | OSNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.351 ms | 0 - 0 MB | NPU
97
+ | OSNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.662 ms | 0 - 0 MB | NPU
98
+ | OSNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.371 ms | 0 - 56 MB | NPU
99
+ | OSNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.671 ms | 0 - 62 MB | NPU
100
+ | OSNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 1.494 ms | 0 - 2 MB | NPU
101
+ | OSNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.548 ms | 0 - 3 MB | NPU
102
+ | OSNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.264 ms | 0 - 44 MB | NPU
103
+ | OSNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.533 ms | 0 - 2 MB | NPU
104
+ | OSNet | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.747 ms | 0 - 48 MB | NPU
105
+ | OSNet | QNN_DLC | w8a8 | Qualcomm® SA8650P | 0.747 ms | 0 - 48 MB | NPU
106
+ | OSNet | QNN_DLC | w8a8 | Qualcomm® SA8255P | 0.747 ms | 0 - 48 MB | NPU
107
+ | OSNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 0.671 ms | 0 - 62 MB | NPU
108
+ | OSNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.62 ms | 0 - 2 MB | NPU
109
+ | OSNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.662 ms | 0 - 0 MB | NPU
110
+ | OSNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 2.803 ms | 0 - 41 MB | NPU
111
+ | OSNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.538 ms | 0 - 44 MB | NPU
112
+ | OSNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.282 ms | 0 - 43 MB | NPU
113
+ | OSNet | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.264 ms | 0 - 44 MB | NPU
114
+ | OSNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.016 ms | 0 - 43 MB | NPU
115
+ | OSNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.282 ms | 0 - 43 MB | NPU
116
+ | OSNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.23 ms | 0 - 45 MB | NPU
117
+ | OSNet | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.538 ms | 0 - 44 MB | NPU
118
+ | OSNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.722 ms | 0 - 59 MB | NPU
119
+ | OSNet | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 2.034 ms | 0 - 63 MB | NPU
120
+ | OSNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 1.468 ms | 0 - 8 MB | NPU
121
+ | OSNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 4.587 ms | 0 - 45 MB | NPU
122
+ | OSNet | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.105 ms | 0 - 2 MB | NPU
123
+ | OSNet | TFLITE | float | Qualcomm® SA8775P | 1.757 ms | 0 - 48 MB | NPU
124
+ | OSNet | TFLITE | float | Qualcomm® SA8650P | 1.757 ms | 0 - 48 MB | NPU
125
+ | OSNet | TFLITE | float | Qualcomm® SA8255P | 1.757 ms | 0 - 48 MB | NPU
126
+ | OSNet | TFLITE | float | Qualcomm® QCS8450 | 2.034 ms | 0 - 63 MB | NPU
127
+ | OSNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1.57 ms | 0 - 7 MB | NPU
128
+ | OSNet | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.537 ms | 0 - 44 MB | NPU
129
+ | OSNet | TFLITE | float | Qualcomm® SA7255P | 4.587 ms | 0 - 45 MB | NPU
130
+ | OSNet | TFLITE | float | Qualcomm® SA8295P | 2.263 ms | 0 - 39 MB | NPU
131
+ | OSNet | TFLITE | float | Snapdragon® 8 Elite Mobile | 0.537 ms | 0 - 44 MB | NPU
132
+ | OSNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.443 ms | 0 - 45 MB | NPU
133
+ | OSNet | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.315 ms | 0 - 52 MB | NPU
134
+ | OSNet | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.588 ms | 0 - 59 MB | NPU
135
+ | OSNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 2.429 ms | 0 - 12 MB | NPU
136
+ | OSNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.492 ms | 0 - 5 MB | NPU
137
+ | OSNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.142 ms | 0 - 41 MB | NPU
138
+ | OSNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.442 ms | 0 - 73 MB | NPU
139
+ | OSNet | TFLITE | w8a8 | Qualcomm® SA8775P | 0.691 ms | 0 - 44 MB | NPU
140
+ | OSNet | TFLITE | w8a8 | Qualcomm® SA8650P | 0.691 ms | 0 - 44 MB | NPU
141
+ | OSNet | TFLITE | w8a8 | Qualcomm® SA8255P | 0.691 ms | 0 - 44 MB | NPU
142
+ | OSNet | TFLITE | w8a8 | Qualcomm® QCS8450 | 0.588 ms | 0 - 59 MB | NPU
143
+ | OSNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.551 ms | 0 - 5 MB | NPU
144
+ | OSNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 3.546 ms | 0 - 40 MB | NPU
145
+ | OSNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.914 ms | 0 - 42 MB | NPU
146
+ | OSNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.257 ms | 0 - 40 MB | NPU
147
+ | OSNet | TFLITE | w8a8 | Qualcomm® SA7255P | 1.142 ms | 0 - 41 MB | NPU
148
+ | OSNet | TFLITE | w8a8 | Qualcomm® SA8295P | 0.922 ms | 0 - 40 MB | NPU
149
+ | OSNet | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.257 ms | 0 - 40 MB | NPU
150
+ | OSNet | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.215 ms | 0 - 43 MB | NPU
151
+ | OSNet | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.914 ms | 0 - 42 MB | NPU
152
+
153
+ ## License
154
+ * The license for the original implementation of OSNet can be found
155
+ [here](https://github.com/KaiyangZhou/deep-person-reid/blob/master/LICENSE).
156
+
157
+ ## References
158
+ * [Omni-Scale Feature Learning for Person Re-Identification](https://arxiv.org/abs/1905.00953)
159
+ * [Source Model Implementation](https://github.com/KaiyangZhou/deep-person-reid)
160
+
161
+ ## Community
162
+ * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
163
+ * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).
release_assets.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.61.0",
3
+ "precisions": {
4
+ "float": {
5
+ "universal_assets": {
6
+ "onnx": {
7
+ "tool_versions": {
8
+ "qairt": "2.45.0.260326154327",
9
+ "onnx_runtime": "1.27.1"
10
+ },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/osnet/releases/v0.61.0/osnet-onnx-float.zip"
12
+ },
13
+ "qnn_dlc": {
14
+ "tool_versions": {
15
+ "qairt": "2.45.0.260326154327"
16
+ },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/osnet/releases/v0.61.0/osnet-qnn_dlc-float.zip"
18
+ },
19
+ "tflite": {
20
+ "tool_versions": {
21
+ "qairt": "2.45.0.260326154327"
22
+ },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/osnet/releases/v0.61.0/osnet-tflite-float.zip"
24
+ }
25
+ }
26
+ },
27
+ "w8a8": {
28
+ "universal_assets": {
29
+ "qnn_dlc": {
30
+ "tool_versions": {
31
+ "qairt": "2.45.0.260326154327"
32
+ },
33
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/osnet/releases/v0.61.0/osnet-qnn_dlc-w8a8.zip"
34
+ },
35
+ "tflite": {
36
+ "tool_versions": {
37
+ "qairt": "2.45.0.260326154327"
38
+ },
39
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/osnet/releases/v0.61.0/osnet-tflite-w8a8.zip"
40
+ }
41
+ }
42
+ }
43
+ }
44
+ }