Hugging Face's logo

qualcomm
/
LiteHRNet

Keypoint Detection
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
a50aa61
·
verified ·
1 Parent(s): 3e900e7

v0.34.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.34.0 for changelog.

Files changed (1) hide show
  1. README.md +14 -23
README.md CHANGED
@@ -23,6 +23,7 @@ More details on model performance across various devices, can be found
23
  [here](https://aihub.qualcomm.com/models/litehrnet).
24
 
25
 
 
26
  ### Model Details
27
 
28
  - **Model Type:** Model_use_case.pose_estimation
@@ -33,20 +34,20 @@ More details on model performance across various devices, can be found
33
 
34
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
35
  |---|---|---|---|---|---|---|---|---|
36
- | LiteHRNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 8.812 ms | 0 - 65 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
37
- | LiteHRNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 5.228 ms | 0 - 68 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
38
- | LiteHRNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 4.51 ms | 0 - 26 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
39
- | LiteHRNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 5.542 ms | 0 - 64 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
40
- | LiteHRNet | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 8.812 ms | 0 - 65 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
41
- | LiteHRNet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 4.553 ms | 0 - 21 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
42
- | LiteHRNet | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 6.483 ms | 0 - 62 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
43
- | LiteHRNet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 4.543 ms | 0 - 23 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
44
- | LiteHRNet | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 5.542 ms | 0 - 64 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
45
- | LiteHRNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 4.587 ms | 0 - 23 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
46
  | LiteHRNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 6.359 ms | 0 - 27 MB | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
47
- | LiteHRNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 2.757 ms | 0 - 71 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
48
  | LiteHRNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.791 ms | 0 - 54 MB | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
49
- | LiteHRNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 2.816 ms | 0 - 64 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
50
  | LiteHRNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.363 ms | 1 - 49 MB | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
51
  | LiteHRNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.476 ms | 4 - 4 MB | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
52
 
@@ -106,17 +107,7 @@ device. This script does the following:
106
  ```bash
107
  python -m qai_hub_models.models.litehrnet.export
108
  ```
109
- ```
110
- Profiling Results
111
- ------------------------------------------------------------
112
- LiteHRNet
113
- Device : cs_8275 (ANDROID 14)
114
- Runtime : TFLITE
115
- Estimated inference time (ms) : 8.8
116
- Estimated peak memory usage (MB): [0, 65]
117
- Total # Ops : 1112
118
- Compute Unit(s) : npu (1110 ops) gpu (0 ops) cpu (2 ops)
119
- ```
120
 
121
 
122
  ## How does this work?
 
23
  [here](https://aihub.qualcomm.com/models/litehrnet).
24
 
25
 
26
+
27
  ### Model Details
28
 
29
  - **Model Type:** Model_use_case.pose_estimation
 
34
 
35
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
+ | LiteHRNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 8.764 ms | 0 - 64 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
38
+ | LiteHRNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 5.134 ms | 0 - 67 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
39
+ | LiteHRNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 4.518 ms | 0 - 23 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
40
+ | LiteHRNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 5.592 ms | 0 - 65 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
41
+ | LiteHRNet | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 8.764 ms | 0 - 64 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
42
+ | LiteHRNet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 4.561 ms | 0 - 20 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
43
+ | LiteHRNet | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 6.426 ms | 0 - 62 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
44
+ | LiteHRNet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 4.557 ms | 0 - 23 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
45
+ | LiteHRNet | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 5.592 ms | 0 - 65 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
46
+ | LiteHRNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 4.518 ms | 0 - 24 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
47
  | LiteHRNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 6.359 ms | 0 - 27 MB | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
48
+ | LiteHRNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 2.761 ms | 0 - 74 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
49
  | LiteHRNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.791 ms | 0 - 54 MB | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
50
+ | LiteHRNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 2.808 ms | 0 - 63 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
51
  | LiteHRNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.363 ms | 1 - 49 MB | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
52
  | LiteHRNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.476 ms | 4 - 4 MB | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
53
 
 
107
  ```bash
108
  python -m qai_hub_models.models.litehrnet.export
109
  ```
110
+
 
 
 
 
 
 
 
 
 
 
111
 
112
 
113
  ## How does this work?