Hugging Face's logo

qualcomm
/
Facial-Landmark-Detection-Quantized

Keypoint Detection
PyTorch
TF Lite
ONNX
quantized
android
Model card Files Community
qaihm-bot commited on
Commit
1410635
·
verified ·
1 Parent(s): bc7099c

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +32 -32
README.md CHANGED
@@ -34,48 +34,47 @@ More details on model performance across various devices, can be found
34
 
35
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
- | Facial-Landmark-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.173 ms | 0 - 7 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
38
- | Facial-Landmark-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.221 ms | 0 - 6 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.so](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.so) |
39
- | Facial-Landmark-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.34 ms | 0 - 12 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.onnx](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.onnx) |
40
- | Facial-Landmark-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.14 ms | 0 - 24 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
41
- | Facial-Landmark-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.18 ms | 0 - 21 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.so](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.so) |
42
- | Facial-Landmark-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.255 ms | 0 - 27 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.onnx](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.onnx) |
43
  | Facial-Landmark-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.128 ms | 0 - 16 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
44
- | Facial-Landmark-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.166 ms | 0 - 16 MB | INT8 | NPU | Use Export Script |
45
- | Facial-Landmark-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.28 ms | 0 - 18 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.onnx](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.onnx) |
46
- | Facial-Landmark-Detection-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 0.522 ms | 0 - 13 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
47
- | Facial-Landmark-Detection-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 0.734 ms | 0 - 12 MB | INT8 | NPU | Use Export Script |
48
- | Facial-Landmark-Detection-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 1.937 ms | 0 - 3 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
49
- | Facial-Landmark-Detection-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.164 ms | 0 - 7 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
50
- | Facial-Landmark-Detection-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.217 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
51
- | Facial-Landmark-Detection-Quantized | SA7255P ADP | SA7255P | TFLITE | 1.203 ms | 0 - 10 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
52
- | Facial-Landmark-Detection-Quantized | SA7255P ADP | SA7255P | QNN | 1.546 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
53
- | Facial-Landmark-Detection-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.167 ms | 0 - 17 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
54
- | Facial-Landmark-Detection-Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.228 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
55
- | Facial-Landmark-Detection-Quantized | SA8295P ADP | SA8295P | TFLITE | 0.456 ms | 0 - 16 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
56
- | Facial-Landmark-Detection-Quantized | SA8295P ADP | SA8295P | QNN | 1.019 ms | 0 - 14 MB | INT8 | NPU | Use Export Script |
57
- | Facial-Landmark-Detection-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.174 ms | 0 - 16 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
58
- | Facial-Landmark-Detection-Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.223 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
59
- | Facial-Landmark-Detection-Quantized | SA8775P ADP | SA8775P | TFLITE | 0.379 ms | 0 - 11 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
60
- | Facial-Landmark-Detection-Quantized | SA8775P ADP | SA8775P | QNN | 0.564 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
61
- | Facial-Landmark-Detection-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.228 ms | 0 - 21 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
62
- | Facial-Landmark-Detection-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.279 ms | 0 - 15 MB | INT8 | NPU | Use Export Script |
63
- | Facial-Landmark-Detection-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.335 ms | 1 - 1 MB | INT8 | NPU | Use Export Script |
64
- | Facial-Landmark-Detection-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.352 ms | 7 - 7 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.onnx](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.onnx) |
65
 
66
 
67
 
68
 
69
  ## Installation
70
 
71
- This model can be installed as a Python package via pip.
72
 
 
73
  ```bash
74
- pip install "qai-hub-models[facemap_3dmm_quantized]"
75
  ```
76
 
77
 
78
-
79
  ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
80
 
81
  Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
@@ -127,7 +126,7 @@ Facial-Landmark-Detection-Quantized
127
  Device : Samsung Galaxy S23 (13)
128
  Runtime : TFLITE
129
  Estimated inference time (ms) : 0.2
130
- Estimated peak memory usage (MB): [0, 7]
131
  Total # Ops : 43
132
  Compute Unit(s) : NPU (43 ops)
133
  ```
@@ -170,7 +169,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
170
 
171
 
172
  ## License
173
- * The license for the original implementation of Facial-Landmark-Detection-Quantized can be found [here](https://github.com/pytorch/vision/blob/main/LICENSE).
 
174
  * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
175
 
176
 
 
34
 
35
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
+ | Facial-Landmark-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.174 ms | 0 - 17 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
38
+ | Facial-Landmark-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.223 ms | 0 - 16 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.so](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.so) |
39
+ | Facial-Landmark-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.367 ms | 0 - 4 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.onnx](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.onnx) |
40
+ | Facial-Landmark-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.14 ms | 0 - 23 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
41
+ | Facial-Landmark-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.179 ms | 0 - 22 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.so](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.so) |
42
+ | Facial-Landmark-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.28 ms | 0 - 23 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.onnx](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.onnx) |
43
  | Facial-Landmark-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.128 ms | 0 - 16 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
44
+ | Facial-Landmark-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.155 ms | 0 - 16 MB | INT8 | NPU | Use Export Script |
45
+ | Facial-Landmark-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.295 ms | 0 - 18 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.onnx](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.onnx) |
46
+ | Facial-Landmark-Detection-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 0.56 ms | 0 - 15 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
47
+ | Facial-Landmark-Detection-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 0.731 ms | 0 - 11 MB | INT8 | NPU | Use Export Script |
48
+ | Facial-Landmark-Detection-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 2.024 ms | 0 - 3 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
49
+ | Facial-Landmark-Detection-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.171 ms | 0 - 17 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
50
+ | Facial-Landmark-Detection-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.22 ms | 0 - 4 MB | INT8 | NPU | Use Export Script |
51
+ | Facial-Landmark-Detection-Quantized | SA7255P ADP | SA7255P | TFLITE | 1.116 ms | 0 - 9 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
52
+ | Facial-Landmark-Detection-Quantized | SA7255P ADP | SA7255P | QNN | 1.367 ms | 0 - 8 MB | INT8 | NPU | Use Export Script |
53
+ | Facial-Landmark-Detection-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.171 ms | 0 - 16 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
54
+ | Facial-Landmark-Detection-Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.213 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
55
+ | Facial-Landmark-Detection-Quantized | SA8295P ADP | SA8295P | TFLITE | 0.455 ms | 0 - 15 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
56
+ | Facial-Landmark-Detection-Quantized | SA8295P ADP | SA8295P | QNN | 0.802 ms | 0 - 14 MB | INT8 | NPU | Use Export Script |
57
+ | Facial-Landmark-Detection-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.177 ms | 0 - 17 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
58
+ | Facial-Landmark-Detection-Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.221 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
59
+ | Facial-Landmark-Detection-Quantized | SA8775P ADP | SA8775P | TFLITE | 0.395 ms | 0 - 10 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
60
+ | Facial-Landmark-Detection-Quantized | SA8775P ADP | SA8775P | QNN | 0.55 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
61
+ | Facial-Landmark-Detection-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.221 ms | 0 - 22 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.tflite) |
62
+ | Facial-Landmark-Detection-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.275 ms | 0 - 20 MB | INT8 | NPU | Use Export Script |
63
+ | Facial-Landmark-Detection-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.282 ms | 1 - 1 MB | INT8 | NPU | Use Export Script |
64
+ | Facial-Landmark-Detection-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.325 ms | 6 - 6 MB | INT8 | NPU | [Facial-Landmark-Detection-Quantized.onnx](https://huggingface.co/qualcomm/Facial-Landmark-Detection-Quantized/blob/main/Facial-Landmark-Detection-Quantized.onnx) |
65
 
66
 
67
 
68
 
69
  ## Installation
70
 
 
71
 
72
+ Install the package via pip:
73
  ```bash
74
+ pip install "qai-hub-models[facemap-3dmm-quantized]"
75
  ```
76
 
77
 
 
78
  ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
79
 
80
  Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
 
126
  Device : Samsung Galaxy S23 (13)
127
  Runtime : TFLITE
128
  Estimated inference time (ms) : 0.2
129
+ Estimated peak memory usage (MB): [0, 17]
130
  Total # Ops : 43
131
  Compute Unit(s) : NPU (43 ops)
132
  ```
 
169
 
170
 
171
  ## License
172
+ * The license for the original implementation of Facial-Landmark-Detection-Quantized can be found
173
+ [here](https://github.com/pytorch/vision/blob/main/LICENSE).
174
  * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
175
 
176