Hugging Face's logo

qualcomm
/
EfficientViT-l2-seg

Image Segmentation
PyTorch
ONNX
real_time
android
Model card Files Community
qaihm-bot commited on
Commit
345b6fb
·
verified ·
1 Parent(s): cdfdc0d

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +15 -13
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
  library_name: pytorch
3
  license: bsd-3-clause
4
- pipeline_tag: image-segmentation
5
  tags:
6
  - real_time
7
  - android
 
8
 
9
  ---
10
 
@@ -36,16 +36,18 @@ More details on model performance across various devices, can be found
36
 
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
- | EfficientViT-l2-seg | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 22178.805 ms | 24 - 124 MB | FP16 | NPU | [EfficientViT-l2-seg.so](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.so) |
40
- | EfficientViT-l2-seg | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1921.957 ms | 5 - 354 MB | FP16 | NPU | [EfficientViT-l2-seg.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.onnx) |
41
- | EfficientViT-l2-seg | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 16480.291 ms | 11 - 455 MB | FP16 | NPU | [EfficientViT-l2-seg.so](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.so) |
42
- | EfficientViT-l2-seg | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 1995.319 ms | 132 - 775 MB | FP16 | NPU | [EfficientViT-l2-seg.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.onnx) |
43
- | EfficientViT-l2-seg | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 19442.548 ms | 24 - 516 MB | FP16 | NPU | Use Export Script |
44
- | EfficientViT-l2-seg | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1445.969 ms | 101 - 809 MB | FP16 | NPU | [EfficientViT-l2-seg.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.onnx) |
45
- | EfficientViT-l2-seg | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 15540.11 ms | 26 - 30 MB | FP16 | NPU | Use Export Script |
46
- | EfficientViT-l2-seg | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 21630.243 ms | 16 - 262 MB | FP16 | NPU | Use Export Script |
47
- | EfficientViT-l2-seg | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 16477.289 ms | 24 - 24 MB | FP16 | NPU | Use Export Script |
48
- | EfficientViT-l2-seg | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2870.496 ms | 144 - 144 MB | FP16 | NPU | [EfficientViT-l2-seg.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.onnx) |
 
 
49
 
50
 
51
 
@@ -109,8 +111,8 @@ Profiling Results
109
  EfficientViT-l2-seg
110
  Device : Samsung Galaxy S23 (13)
111
  Runtime : QNN
112
- Estimated inference time (ms) : 22178.8
113
- Estimated peak memory usage (MB): [24, 124]
114
  Total # Ops : 775
115
  Compute Unit(s) : NPU (775 ops)
116
  ```
 
1
  ---
2
  library_name: pytorch
3
  license: bsd-3-clause
 
4
  tags:
5
  - real_time
6
  - android
7
+ pipeline_tag: image-segmentation
8
 
9
  ---
10
 
 
36
 
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | EfficientViT-l2-seg | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 15656.209 ms | 24 - 26 MB | FP16 | NPU | [EfficientViT-l2-seg.so](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.so) |
40
+ | EfficientViT-l2-seg | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1739.493 ms | 10 - 421 MB | FP16 | NPU | [EfficientViT-l2-seg.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.onnx) |
41
+ | EfficientViT-l2-seg | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 11581.359 ms | 25 - 42 MB | FP16 | NPU | [EfficientViT-l2-seg.so](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.so) |
42
+ | EfficientViT-l2-seg | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 1691.954 ms | 136 - 783 MB | FP16 | NPU | [EfficientViT-l2-seg.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.onnx) |
43
+ | EfficientViT-l2-seg | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 19160.309 ms | 24 - 516 MB | FP16 | NPU | Use Export Script |
44
+ | EfficientViT-l2-seg | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1446.649 ms | 102 - 810 MB | FP16 | NPU | [EfficientViT-l2-seg.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.onnx) |
45
+ | EfficientViT-l2-seg | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 34423.255 ms | 23 - 31 MB | FP16 | NPU | Use Export Script |
46
+ | EfficientViT-l2-seg | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 15535.893 ms | 24 - 26 MB | FP16 | NPU | Use Export Script |
47
+ | EfficientViT-l2-seg | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 19541.213 ms | 24 - 32 MB | FP16 | NPU | Use Export Script |
48
+ | EfficientViT-l2-seg | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 21617.084 ms | 19 - 263 MB | FP16 | NPU | Use Export Script |
49
+ | EfficientViT-l2-seg | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 16618.714 ms | 24 - 24 MB | FP16 | NPU | Use Export Script |
50
+ | EfficientViT-l2-seg | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2878.628 ms | 144 - 144 MB | FP16 | NPU | [EfficientViT-l2-seg.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.onnx) |
51
 
52
 
53
 
 
111
  EfficientViT-l2-seg
112
  Device : Samsung Galaxy S23 (13)
113
  Runtime : QNN
114
+ Estimated inference time (ms) : 15656.2
115
+ Estimated peak memory usage (MB): [24, 26]
116
  Total # Ops : 775
117
  Compute Unit(s) : NPU (775 ops)
118
  ```