Hugging Face's logo

qualcomm
/
Depth-Anything-V2

Depth Estimation
PyTorch
LiteRT
android
Model card Files
xet
Community
1
qaihm-bot commited on
Commit
f446ab1
·
verified ·
1 Parent(s): 656abc2

v0.32.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.32.0 for changelog.

Files changed (5) hide show
  1. .gitattributes +1 -0
  2. DEPLOYMENT_MODEL_LICENSE.pdf +3 -0
  3. Depth-Anything-V2.onnx +2 -2
  4. LICENSE +2 -0
  5. README.md +6 -6
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  Depth-Anything-V2.so filter=lfs diff=lfs merge=lfs -text
37
  Depth-Anything-V2.dlc filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  Depth-Anything-V2.so filter=lfs diff=lfs merge=lfs -text
37
  Depth-Anything-V2.dlc filter=lfs diff=lfs merge=lfs -text
38
+ DEPLOYMENT_MODEL_LICENSE.pdf filter=lfs diff=lfs merge=lfs -text
DEPLOYMENT_MODEL_LICENSE.pdf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4409f93b0e82531303b3e10f52f1fdfb56467a25f05b7441c6bbd8bb8a64b42c
3
+ size 109629
Depth-Anything-V2.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f14129c1231b1061cb91856bed9b216425b0081056079cc7875c593bafe32d0f
3
- size 99014828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:943e16afd536809f8ad495ed699828ffc7109b1d9667a549d9810b0f5f5bd51e
3
+ size 99032010
LICENSE ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ The license of the original trained model can be found at https://github.com/huggingface/transformers/blob/main/LICENSE.
2
+ The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.
README.md CHANGED
@@ -29,8 +29,8 @@ More details on model performance across various devices, can be found
29
  - **Model Stats:**
30
  - Model checkpoint: DepthAnything_V2_Small
31
  - Input resolution: 518x518
32
- - Number of parameters: 24.8M
33
- - Model size: 94 MB
34
 
35
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
@@ -54,15 +54,15 @@ More details on model performance across various devices, can be found
54
  | Depth-Anything-V2 | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 130.392 ms | 0 - 727 MB | NPU | [Depth-Anything-V2.dlc](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.dlc) |
55
  | Depth-Anything-V2 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 139.704 ms | 1 - 104 MB | NPU | [Depth-Anything-V2.tflite](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.tflite) |
56
  | Depth-Anything-V2 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 126.633 ms | 3 - 99 MB | NPU | [Depth-Anything-V2.dlc](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.dlc) |
57
- | Depth-Anything-V2 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 145.174 ms | 1 - 278 MB | NPU | [Depth-Anything-V2.onnx](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.onnx) |
58
  | Depth-Anything-V2 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 110.154 ms | 0 - 588 MB | NPU | [Depth-Anything-V2.tflite](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.tflite) |
59
  | Depth-Anything-V2 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 99.403 ms | 3 - 727 MB | NPU | [Depth-Anything-V2.dlc](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.dlc) |
60
- | Depth-Anything-V2 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 111.993 ms | 0 - 802 MB | NPU | [Depth-Anything-V2.onnx](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.onnx) |
61
  | Depth-Anything-V2 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 98.794 ms | 0 - 562 MB | NPU | [Depth-Anything-V2.tflite](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.tflite) |
62
  | Depth-Anything-V2 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 88.965 ms | 3 - 787 MB | NPU | [Depth-Anything-V2.dlc](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.dlc) |
63
- | Depth-Anything-V2 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 91.695 ms | 5 - 887 MB | NPU | [Depth-Anything-V2.onnx](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.onnx) |
64
  | Depth-Anything-V2 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 141.971 ms | 123 - 123 MB | NPU | [Depth-Anything-V2.dlc](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.dlc) |
65
- | Depth-Anything-V2 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 143.769 ms | 67 - 67 MB | NPU | [Depth-Anything-V2.onnx](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.onnx) |
66
 
67
 
68
 
 
29
  - **Model Stats:**
30
  - Model checkpoint: DepthAnything_V2_Small
31
  - Input resolution: 518x518
32
+ - Number of parameters: 24.7M
33
+ - Model size (float): 94.3 MB
34
 
35
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
 
54
  | Depth-Anything-V2 | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 130.392 ms | 0 - 727 MB | NPU | [Depth-Anything-V2.dlc](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.dlc) |
55
  | Depth-Anything-V2 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 139.704 ms | 1 - 104 MB | NPU | [Depth-Anything-V2.tflite](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.tflite) |
56
  | Depth-Anything-V2 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 126.633 ms | 3 - 99 MB | NPU | [Depth-Anything-V2.dlc](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.dlc) |
57
+ | Depth-Anything-V2 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 146.717 ms | 2 - 205 MB | NPU | [Depth-Anything-V2.onnx](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.onnx) |
58
  | Depth-Anything-V2 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 110.154 ms | 0 - 588 MB | NPU | [Depth-Anything-V2.tflite](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.tflite) |
59
  | Depth-Anything-V2 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 99.403 ms | 3 - 727 MB | NPU | [Depth-Anything-V2.dlc](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.dlc) |
60
+ | Depth-Anything-V2 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 110.155 ms | 3 - 802 MB | NPU | [Depth-Anything-V2.onnx](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.onnx) |
61
  | Depth-Anything-V2 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 98.794 ms | 0 - 562 MB | NPU | [Depth-Anything-V2.tflite](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.tflite) |
62
  | Depth-Anything-V2 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 88.965 ms | 3 - 787 MB | NPU | [Depth-Anything-V2.dlc](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.dlc) |
63
+ | Depth-Anything-V2 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 92.793 ms | 5 - 890 MB | NPU | [Depth-Anything-V2.onnx](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.onnx) |
64
  | Depth-Anything-V2 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 141.971 ms | 123 - 123 MB | NPU | [Depth-Anything-V2.dlc](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.dlc) |
65
+ | Depth-Anything-V2 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 143.468 ms | 67 - 67 MB | NPU | [Depth-Anything-V2.onnx](https://huggingface.co/qualcomm/Depth-Anything-V2/blob/main/Depth-Anything-V2.onnx) |
66
 
67
 
68