Hugging Face's logo

qualcomm
/
Depth-Anything-V2

Depth Estimation
PyTorch
android
Model card Files
xet
 Community
1
qaihm-bot commited on
Commit
fcf55f2
·
verified ·
1 Parent(s): 995e600

v0.48.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.48.0 for changelog.

Files changed (1) hide show
  1. README.md +37 -37
README.md CHANGED
@@ -14,7 +14,7 @@ pipeline_tag: depth-estimation
14
  Depth Anything is designed for estimating depth at each point in an image.
15
 
16
  This is based on the implementation of Depth-Anything-V2 found [here](https://github.com/huggingface/transformers/tree/main/src/transformers/models/depth_anything).
17
- This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/depth_anything_v2) 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
 
@@ -27,25 +27,25 @@ 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/depth_anything_v2/releases/v0.47.0/depth_anything_v2-onnx-float.zip)
31
- | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/depth_anything_v2/releases/v0.47.0/depth_anything_v2-onnx-w8a16.zip)
32
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/depth_anything_v2/releases/v0.47.0/depth_anything_v2-qnn_dlc-float.zip)
33
- | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/depth_anything_v2/releases/v0.47.0/depth_anything_v2-qnn_dlc-w8a16.zip)
34
- | 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/depth_anything_v2/releases/v0.47.0/depth_anything_v2-tflite-float.zip)
35
 
36
  For more device-specific assets and performance metrics, visit **[Depth-Anything-V2 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/depth_anything_v2)**.
37
 
38
 
39
  ### Option 2: Export with Custom Configurations
40
 
41
- Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/depth_anything_v2) Python library to compile and export the model with your own:
42
  - Custom weights (e.g., fine-tuned checkpoints)
43
  - Custom input shapes
44
  - Target device and runtime configurations
45
 
46
  This option is ideal if you need to customize the model beyond the default configuration provided here.
47
 
48
- See our repository for [Depth-Anything-V2 on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/depth_anything_v2) for usage instructions.
49
 
50
  ## Model Details
51
 
@@ -60,35 +60,35 @@ See our repository for [Depth-Anything-V2 on GitHub](https://github.com/quic/ai-
60
  ## Performance Summary
61
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
62
  |---|---|---|---|---|---|---
63
- | Depth-Anything-V2 | ONNX | float | Snapdragon® X Elite | 79.498 ms | 50 - 50 MB | NPU
64
- | Depth-Anything-V2 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 56.02 ms | 0 - 869 MB | NPU
65
- | Depth-Anything-V2 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 77.217 ms | 1 - 57 MB | NPU
66
- | Depth-Anything-V2 | ONNX | float | Qualcomm® QCS9075 | 98.337 ms | 3 - 9 MB | NPU
67
- | Depth-Anything-V2 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 41.638 ms | 2 - 585 MB | NPU
68
- | Depth-Anything-V2 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 35.163 ms | 5 - 660 MB | NPU
69
- | Depth-Anything-V2 | ONNX | float | Snapdragon® X2 Elite | 34.392 ms | 51 - 51 MB | NPU
70
- | Depth-Anything-V2 | QNN_DLC | float | Snapdragon® X Elite | 76.394 ms | 3 - 3 MB | NPU
71
- | Depth-Anything-V2 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 54.681 ms | 0 - 662 MB | NPU
72
- | Depth-Anything-V2 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 176.558 ms | 1 - 487 MB | NPU
73
- | Depth-Anything-V2 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 74.594 ms | 3 - 546 MB | NPU
74
- | Depth-Anything-V2 | QNN_DLC | float | Qualcomm® SA8775P | 80.878 ms | 0 - 495 MB | NPU
75
- | Depth-Anything-V2 | QNN_DLC | float | Qualcomm® QCS9075 | 96.792 ms | 3 - 9 MB | NPU
76
- | Depth-Anything-V2 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 114.765 ms | 1 - 601 MB | NPU
77
- | Depth-Anything-V2 | QNN_DLC | float | Qualcomm® SA7255P | 176.558 ms | 1 - 487 MB | NPU
78
- | Depth-Anything-V2 | QNN_DLC | float | Qualcomm® SA8295P | 106.143 ms | 0 - 484 MB | NPU
79
- | Depth-Anything-V2 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 40.859 ms | 3 - 494 MB | NPU
80
- | Depth-Anything-V2 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 36.599 ms | 3 - 504 MB | NPU
81
- | Depth-Anything-V2 | QNN_DLC | float | Snapdragon® X2 Elite | 34.631 ms | 3 - 3 MB | NPU
82
- | Depth-Anything-V2 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 50.873 ms | 0 - 598 MB | NPU
83
- | Depth-Anything-V2 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 173.811 ms | 0 - 443 MB | NPU
84
- | Depth-Anything-V2 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 73.102 ms | 1 - 11 MB | NPU
85
- | Depth-Anything-V2 | TFLITE | float | Qualcomm® SA8775P | 377.672 ms | 1 - 444 MB | NPU
86
- | Depth-Anything-V2 | TFLITE | float | Qualcomm® QCS9075 | 89.535 ms | 1 - 58 MB | NPU
87
- | Depth-Anything-V2 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 104.641 ms | 0 - 583 MB | NPU
88
- | Depth-Anything-V2 | TFLITE | float | Qualcomm® SA7255P | 173.811 ms | 0 - 443 MB | NPU
89
- | Depth-Anything-V2 | TFLITE | float | Qualcomm® SA8295P | 100.289 ms | 1 - 471 MB | NPU
90
- | Depth-Anything-V2 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 35.345 ms | 1 - 454 MB | NPU
91
- | Depth-Anything-V2 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 31.24 ms | 1 - 466 MB | NPU
92
 
93
  ## License
94
  * The license for the original implementation of Depth-Anything-V2 can be found
 
14
  Depth Anything is designed for estimating depth at each point in an image.
15
 
16
  This is based on the implementation of Depth-Anything-V2 found [here](https://github.com/huggingface/transformers/tree/main/src/transformers/models/depth_anything).
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/depth_anything_v2) 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
 
 
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/depth_anything_v2/releases/v0.48.0/depth_anything_v2-onnx-float.zip)
31
+ | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/depth_anything_v2/releases/v0.48.0/depth_anything_v2-onnx-w8a16.zip)
32
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/depth_anything_v2/releases/v0.48.0/depth_anything_v2-qnn_dlc-float.zip)
33
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/depth_anything_v2/releases/v0.48.0/depth_anything_v2-qnn_dlc-w8a16.zip)
34
+ | 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/depth_anything_v2/releases/v0.48.0/depth_anything_v2-tflite-float.zip)
35
 
36
  For more device-specific assets and performance metrics, visit **[Depth-Anything-V2 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/depth_anything_v2)**.
37
 
38
 
39
  ### Option 2: Export with Custom Configurations
40
 
41
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/depth_anything_v2) Python library to compile and export the model with your own:
42
  - Custom weights (e.g., fine-tuned checkpoints)
43
  - Custom input shapes
44
  - Target device and runtime configurations
45
 
46
  This option is ideal if you need to customize the model beyond the default configuration provided here.
47
 
48
+ See our repository for [Depth-Anything-V2 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/depth_anything_v2) for usage instructions.
49
 
50
  ## Model Details
51
 
 
60
  ## Performance Summary
61
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
62
  |---|---|---|---|---|---|---
63
+ | Depth-Anything-V2 | ONNX | float | Snapdragon® X2 Elite | 34.613 ms | 51 - 51 MB | NPU
64
+ | Depth-Anything-V2 | ONNX | float | Snapdragon® X Elite | 79.587 ms | 50 - 50 MB | NPU
65
+ | Depth-Anything-V2 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 54.907 ms | 0 - 849 MB | NPU
66
+ | Depth-Anything-V2 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 76.098 ms | 0 - 68 MB | NPU
67
+ | Depth-Anything-V2 | ONNX | float | Qualcomm® QCS9075 | 98.824 ms | 3 - 9 MB | NPU
68
+ | Depth-Anything-V2 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 41.513 ms | 2 - 586 MB | NPU
69
+ | Depth-Anything-V2 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 34.633 ms | 5 - 660 MB | NPU
70
+ | Depth-Anything-V2 | QNN_DLC | float | Snapdragon® X2 Elite | 34.633 ms | 3 - 3 MB | NPU
71
+ | Depth-Anything-V2 | QNN_DLC | float | Snapdragon® X Elite | 76.4 ms | 3 - 3 MB | NPU
72
+ | Depth-Anything-V2 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 54.928 ms | 3 - 669 MB | NPU
73
+ | Depth-Anything-V2 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 176.687 ms | 1 - 486 MB | NPU
74
+ | Depth-Anything-V2 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 74.543 ms | 3 - 6 MB | NPU
75
+ | Depth-Anything-V2 | QNN_DLC | float | Qualcomm® SA8775P | 80.991 ms | 1 - 496 MB | NPU
76
+ | Depth-Anything-V2 | QNN_DLC | float | Qualcomm® QCS9075 | 96.558 ms | 3 - 9 MB | NPU
77
+ | Depth-Anything-V2 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 115.581 ms | 1 - 602 MB | NPU
78
+ | Depth-Anything-V2 | QNN_DLC | float | Qualcomm® SA7255P | 176.687 ms | 1 - 486 MB | NPU
79
+ | Depth-Anything-V2 | QNN_DLC | float | Qualcomm® SA8295P | 106.129 ms | 0 - 484 MB | NPU
80
+ | Depth-Anything-V2 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 40.517 ms | 1 - 493 MB | NPU
81
+ | Depth-Anything-V2 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 36.034 ms | 2 - 503 MB | NPU
82
+ | Depth-Anything-V2 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 50.806 ms | 0 - 589 MB | NPU
83
+ | Depth-Anything-V2 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 173.857 ms | 1 - 444 MB | NPU
84
+ | Depth-Anything-V2 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 72.541 ms | 1 - 8 MB | NPU
85
+ | Depth-Anything-V2 | TFLITE | float | Qualcomm® SA8775P | 377.558 ms | 1 - 445 MB | NPU
86
+ | Depth-Anything-V2 | TFLITE | float | Qualcomm® QCS9075 | 89.524 ms | 1 - 58 MB | NPU
87
+ | Depth-Anything-V2 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 105.077 ms | 1 - 585 MB | NPU
88
+ | Depth-Anything-V2 | TFLITE | float | Qualcomm® SA7255P | 173.857 ms | 1 - 444 MB | NPU
89
+ | Depth-Anything-V2 | TFLITE | float | Qualcomm® SA8295P | 100.216 ms | 1 - 471 MB | NPU
90
+ | Depth-Anything-V2 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 35.628 ms | 1 - 459 MB | NPU
91
+ | Depth-Anything-V2 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 31.521 ms | 1 - 466 MB | NPU
92
 
93
  ## License
94
  * The license for the original implementation of Depth-Anything-V2 can be found