Hugging Face's logo

qualcomm
/
LiteHRNet

Keypoint Detection
PyTorch
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
80f27fa
·
verified ·
1 Parent(s): acf31fa

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +14 -13
README.md CHANGED
@@ -33,18 +33,19 @@ More details on model performance across various devices, can be found
33
 
34
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
35
  |---|---|---|---|---|---|---|---|---|
36
- | LiteHRNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 7.959 ms | 0 - 3 MB | FP16 | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
37
- | LiteHRNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 7.13 ms | 0 - 7 MB | FP16 | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
38
- | LiteHRNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 4.91 ms | 0 - 95 MB | FP16 | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
39
- | LiteHRNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 4.533 ms | 1 - 107 MB | FP16 | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
40
- | LiteHRNet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 7.938 ms | 0 - 2 MB | FP16 | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
41
- | LiteHRNet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 7.965 ms | 0 - 3 MB | FP16 | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
42
- | LiteHRNet | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 7.929 ms | 0 - 2 MB | FP16 | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
43
- | LiteHRNet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 7.934 ms | 0 - 3 MB | FP16 | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
44
- | LiteHRNet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 8.522 ms | 0 - 84 MB | FP16 | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
45
- | LiteHRNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 5.295 ms | 0 - 68 MB | FP16 | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
46
- | LiteHRNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 4.83 ms | 1 - 80 MB | FP16 | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
47
- | LiteHRNet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.063 ms | 4 - 4 MB | FP16 | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
 
48
 
49
 
50
 
@@ -110,7 +111,7 @@ LiteHRNet
110
  Device : Samsung Galaxy S23 (13)
111
  Runtime : TFLITE
112
  Estimated inference time (ms) : 8.0
113
- Estimated peak memory usage (MB): [0, 3]
114
  Total # Ops : 1235
115
  Compute Unit(s) : NPU (1233 ops) CPU (2 ops)
116
  ```
 
33
 
34
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
35
  |---|---|---|---|---|---|---|---|---|
36
+ | LiteHRNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 7.964 ms | 0 - 2 MB | FP16 | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
37
+ | LiteHRNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 7.227 ms | 0 - 6 MB | FP16 | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
38
+ | LiteHRNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 4.895 ms | 0 - 96 MB | FP16 | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
39
+ | LiteHRNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 4.516 ms | 1 - 108 MB | FP16 | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
40
+ | LiteHRNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 4.319 ms | 0 - 68 MB | FP16 | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
41
+ | LiteHRNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 4.826 ms | 1 - 79 MB | FP16 | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
42
+ | LiteHRNet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 7.935 ms | 0 - 3 MB | FP16 | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
43
+ | LiteHRNet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 7.949 ms | 0 - 149 MB | FP16 | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
44
+ | LiteHRNet | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 7.939 ms | 0 - 3 MB | FP16 | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
45
+ | LiteHRNet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 7.939 ms | 0 - 3 MB | FP16 | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
46
+ | LiteHRNet | SA8295P ADP | SA8295P | TFLITE | 9.976 ms | 0 - 61 MB | FP16 | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
47
+ | LiteHRNet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 8.571 ms | 0 - 84 MB | FP16 | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
48
+ | LiteHRNet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.118 ms | 5 - 5 MB | FP16 | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
49
 
50
 
51
 
 
111
  Device : Samsung Galaxy S23 (13)
112
  Runtime : TFLITE
113
  Estimated inference time (ms) : 8.0
114
+ Estimated peak memory usage (MB): [0, 2]
115
  Total # Ops : 1235
116
  Compute Unit(s) : NPU (1233 ops) CPU (2 ops)
117
  ```