Hugging Face's logo

qualcomm
/
LiteHRNet

Keypoint Detection
PyTorch
LiteRT
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
f73bf0a
·
verified ·
1 Parent(s): fc34654

v0.30.5

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.30.5 for changelog.

Files changed (1) hide show
  1. README.md +20 -20
README.md CHANGED
@@ -33,22 +33,22 @@ 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 | 8.964 ms | 0 - 51 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
37
- | LiteHRNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 5.419 ms | 0 - 63 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
38
- | LiteHRNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 4.582 ms | 0 - 15 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
39
- | LiteHRNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 5.656 ms | 0 - 52 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
40
- | LiteHRNet | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 8.964 ms | 0 - 51 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
41
- | LiteHRNet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 4.597 ms | 0 - 18 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
42
- | LiteHRNet | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 6.413 ms | 0 - 54 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
43
- | LiteHRNet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 4.635 ms | 0 - 17 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
44
- | LiteHRNet | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 5.656 ms | 0 - 52 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 | 4.608 ms | 0 - 15 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 | 7.537 ms | 0 - 24 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 | 2.853 ms | 0 - 62 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 | 4.494 ms | 1 - 59 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 | 2.871 ms | 0 - 52 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 | 4.044 ms | 1 - 52 MB | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
51
- | LiteHRNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.008 ms | 4 - 4 MB | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
52
 
53
 
54
 
@@ -112,8 +112,8 @@ Profiling Results
112
  LiteHRNet
113
  Device : cs_8275 (ANDROID 14)
114
  Runtime : TFLITE
115
- Estimated inference time (ms) : 9.0
116
- Estimated peak memory usage (MB): [0, 51]
117
  Total # Ops : 1113
118
  Compute Unit(s) : npu (1111 ops) gpu (0 ops) cpu (2 ops)
119
  ```
@@ -202,13 +202,13 @@ AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
202
  You can also run the demo on-device.
203
 
204
  ```bash
205
- python -m qai_hub_models.models.litehrnet.demo --on-device
206
  ```
207
 
208
  **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
209
  environment, please add the following to your cell (instead of the above).
210
  ```
211
- %run -m qai_hub_models.models.litehrnet.demo -- --on-device
212
  ```
213
 
214
 
 
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 | 24.057 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 | 5.303 ms | 0 - 67 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
38
+ | LiteHRNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 4.608 ms | 0 - 23 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
39
+ | LiteHRNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 5.598 ms | 0 - 64 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
40
+ | LiteHRNet | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 24.057 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 | 4.6 ms | 0 - 19 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
42
+ | LiteHRNet | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 6.528 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 | 4.629 ms | 0 - 23 MB | NPU | [LiteHRNet.tflite](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.tflite) |
44
+ | LiteHRNet | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 5.598 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 | 4.634 ms | 0 - 20 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 | 5.998 ms | 0 - 23 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 | 2.768 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 | 3.749 ms | 0 - 57 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 | 2.359 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 | 4.014 ms | 0 - 52 MB | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
51
+ | LiteHRNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.494 ms | 4 - 4 MB | NPU | [LiteHRNet.onnx](https://huggingface.co/qualcomm/LiteHRNet/blob/main/LiteHRNet.onnx) |
52
 
53
 
54
 
 
112
  LiteHRNet
113
  Device : cs_8275 (ANDROID 14)
114
  Runtime : TFLITE
115
+ Estimated inference time (ms) : 24.1
116
+ Estimated peak memory usage (MB): [0, 65]
117
  Total # Ops : 1113
118
  Compute Unit(s) : npu (1111 ops) gpu (0 ops) cpu (2 ops)
119
  ```
 
202
  You can also run the demo on-device.
203
 
204
  ```bash
205
+ python -m qai_hub_models.models.litehrnet.demo --eval-mode on-device
206
  ```
207
 
208
  **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
209
  environment, please add the following to your cell (instead of the above).
210
  ```
211
+ %run -m qai_hub_models.models.litehrnet.demo -- --eval-mode on-device
212
  ```
213
 
214