Hugging Face's logo

qualcomm
/
StereoNet

Depth Estimation
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
4003b1c
·
verified ·
1 Parent(s): 708f44b

v0.50.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.50.0 for changelog.

Files changed (3) hide show
  1. LICENSE +1 -0
  2. README.md +99 -0
  3. release_assets.json +1 -0
LICENSE ADDED
@@ -0,0 +1 @@
 
 
1
+ The license of the original trained model can be found at https://github.com/andrewlstewart/StereoNet_PyTorch/blob/main/LICENSE.
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: pytorch
3
+ license: other
4
+ tags:
5
+ - android
6
+ pipeline_tag: depth-estimation
7
+
8
+ ---
9
+
10
+ ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stereonet/web-assets/model_demo.png)
11
+
12
+ # StereoNet: Optimized for Qualcomm Devices
13
+
14
+ StereoNet is an end-to-end deep architecture for real-time stereo matching that produces high-quality, edge-preserved disparity maps from a rectified stereo image pair.
15
+
16
+ This is based on the implementation of StereoNet found [here](https://github.com/andrewlstewart/StereoNet_PyTorch).
17
+ 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/qai_hub_models/models/stereonet) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
18
+
19
+ 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.
20
+
21
+ ## Getting Started
22
+ There are two ways to deploy this model on your device:
23
+
24
+ ### Option 1: Download Pre-Exported Models
25
+
26
+ Below are pre-exported model assets ready for deployment.
27
+
28
+ | Runtime | Precision | Chipset | SDK Versions | Download |
29
+ |---|---|---|---|---|
30
+ | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stereonet/releases/v0.50.0/stereonet-onnx-float.zip)
31
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stereonet/releases/v0.50.0/stereonet-qnn_dlc-float.zip)
32
+ | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stereonet/releases/v0.50.0/stereonet-tflite-float.zip)
33
+
34
+ For more device-specific assets and performance metrics, visit **[StereoNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/stereonet)**.
35
+
36
+
37
+ ### Option 2: Export with Custom Configurations
38
+
39
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/stereonet) Python library to compile and export the model with your own:
40
+ - Custom weights (e.g., fine-tuned checkpoints)
41
+ - Custom input shapes
42
+ - Target device and runtime configurations
43
+
44
+ This option is ideal if you need to customize the model beyond the default configuration provided here.
45
+
46
+ See our repository for [StereoNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/stereonet) for usage instructions.
47
+
48
+ ## Model Details
49
+
50
+ **Model Type:** Model_use_case.depth_estimation
51
+
52
+ **Model Stats:**
53
+ - Model checkpoint: KeystoneDepth (epoch=21-step=696366.ckpt)
54
+ - Input resolution: 786x490
55
+ - Number of parameters: 1.94M
56
+ - Model size (float): 7.41 MB
57
+
58
+ ## Performance Summary
59
+ | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
60
+ |---|---|---|---|---|---|---
61
+ | StereoNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 184.46 ms | 6 - 1360 MB | NPU
62
+ | StereoNet | ONNX | float | Snapdragon® X2 Elite | 180.253 ms | 20 - 20 MB | NPU
63
+ | StereoNet | ONNX | float | Snapdragon® X Elite | 329.003 ms | 20 - 20 MB | NPU
64
+ | StereoNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 261.796 ms | 6 - 1980 MB | NPU
65
+ | StereoNet | ONNX | float | Qualcomm® QCS8550 (Proxy) | 391.508 ms | 0 - 1078 MB | NPU
66
+ | StereoNet | ONNX | float | Qualcomm® QCS9075 | 514.272 ms | 3 - 6 MB | NPU
67
+ | StereoNet | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 219.257 ms | 3 - 1326 MB | NPU
68
+ | StereoNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 164.683 ms | 3 - 1355 MB | NPU
69
+ | StereoNet | QNN_DLC | float | Snapdragon® X2 Elite | 163.103 ms | 3 - 3 MB | NPU
70
+ | StereoNet | QNN_DLC | float | Snapdragon® X Elite | 313.701 ms | 3 - 3 MB | NPU
71
+ | StereoNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 246.971 ms | 3 - 1992 MB | NPU
72
+ | StereoNet | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 1207.886 ms | 2 - 1362 MB | NPU
73
+ | StereoNet | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 336.051 ms | 3 - 5 MB | NPU
74
+ | StereoNet | QNN_DLC | float | Qualcomm® SA8775P | 1789.115 ms | 1 - 1362 MB | NPU
75
+ | StereoNet | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 766.006 ms | 3 - 2149 MB | NPU
76
+ | StereoNet | QNN_DLC | float | Qualcomm® SA7255P | 1207.886 ms | 2 - 1362 MB | NPU
77
+ | StereoNet | QNN_DLC | float | Qualcomm® SA8295P | 474.277 ms | 0 - 1499 MB | NPU
78
+ | StereoNet | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 202.351 ms | 0 - 1333 MB | NPU
79
+ | StereoNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 230.663 ms | 72 - 1694 MB | NPU
80
+ | StereoNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 312.911 ms | 73 - 2203 MB | NPU
81
+ | StereoNet | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 1322.775 ms | 73 - 1627 MB | NPU
82
+ | StereoNet | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 456.107 ms | 74 - 78 MB | NPU
83
+ | StereoNet | TFLITE | float | Qualcomm® SA8775P | 526.555 ms | 74 - 1628 MB | NPU
84
+ | StereoNet | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 766.181 ms | 74 - 2482 MB | NPU
85
+ | StereoNet | TFLITE | float | Qualcomm® SA7255P | 1322.775 ms | 73 - 1627 MB | NPU
86
+ | StereoNet | TFLITE | float | Qualcomm® SA8295P | 562.674 ms | 74 - 1726 MB | NPU
87
+ | StereoNet | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 254.335 ms | 72 - 1657 MB | NPU
88
+
89
+ ## License
90
+ * The license for the original implementation of StereoNet can be found
91
+ [here](https://github.com/andrewlstewart/StereoNet_PyTorch/blob/main/LICENSE).
92
+
93
+ ## References
94
+ * [StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction](https://arxiv.org/abs/1807.08865)
95
+ * [Source Model Implementation](https://github.com/andrewlstewart/StereoNet_PyTorch)
96
+
97
+ ## Community
98
+ * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
99
+ * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).
release_assets.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"version":"0.50.0","precisions":{"float":{"universal_assets":{"tflite":{"tool_versions":{"qairt":"2.43.0.260127150333_193827","tflite":"2.17.0"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stereonet/releases/v0.50.0/stereonet-tflite-float.zip"},"qnn_dlc":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stereonet/releases/v0.50.0/stereonet-qnn_dlc-float.zip"},"onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.1"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stereonet/releases/v0.50.0/stereonet-onnx-float.zip"}}}}}