Hugging Face's logo

qualcomm
/
YOLOv8-Segmentation

Image Segmentation
PyTorch
TF Lite
ONNX
real_time
android
Model card Files Community
qaihm-bot commited on
Commit
7e15abb
·
verified ·
1 Parent(s): 6ada1a2

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +31 -31
README.md CHANGED
@@ -36,45 +36,44 @@ 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
- | YOLOv8-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 6.501 ms | 4 - 29 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
40
- | YOLOv8-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 6.41 ms | 5 - 15 MB | FP16 | NPU | [YOLOv8-Segmentation.so](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.so) |
41
- | YOLOv8-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 7.625 ms | 14 - 49 MB | FP16 | NPU | [YOLOv8-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.onnx) |
42
- | YOLOv8-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 4.781 ms | 0 - 52 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
43
- | YOLOv8-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 4.575 ms | 0 - 58 MB | FP16 | NPU | [YOLOv8-Segmentation.so](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.so) |
44
- | YOLOv8-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 5.178 ms | 16 - 77 MB | FP16 | NPU | [YOLOv8-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.onnx) |
45
- | YOLOv8-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 4.567 ms | 3 - 53 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
46
- | YOLOv8-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 4.615 ms | 5 - 58 MB | FP16 | NPU | Use Export Script |
47
- | YOLOv8-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 4.04 ms | 17 - 69 MB | FP16 | NPU | [YOLOv8-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.onnx) |
48
- | YOLOv8-Segmentation | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 6.48 ms | 4 - 23 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
49
- | YOLOv8-Segmentation | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 6.285 ms | 5 - 8 MB | FP16 | NPU | Use Export Script |
50
- | YOLOv8-Segmentation | SA7255P ADP | SA7255P | TFLITE | 93.405 ms | 4 - 51 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
51
- | YOLOv8-Segmentation | SA7255P ADP | SA7255P | QNN | 92.376 ms | 3 - 13 MB | FP16 | NPU | Use Export Script |
52
- | YOLOv8-Segmentation | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 6.501 ms | 4 - 27 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
53
- | YOLOv8-Segmentation | SA8255 (Proxy) | SA8255P Proxy | QNN | 6.38 ms | 5 - 7 MB | FP16 | NPU | Use Export Script |
54
- | YOLOv8-Segmentation | SA8295P ADP | SA8295P | TFLITE | 11.44 ms | 4 - 42 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
55
- | YOLOv8-Segmentation | SA8295P ADP | SA8295P | QNN | 10.306 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
56
- | YOLOv8-Segmentation | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 6.516 ms | 4 - 26 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
57
- | YOLOv8-Segmentation | SA8650 (Proxy) | SA8650P Proxy | QNN | 6.323 ms | 5 - 7 MB | FP16 | NPU | Use Export Script |
58
- | YOLOv8-Segmentation | SA8775P ADP | SA8775P | TFLITE | 10.15 ms | 4 - 50 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
59
- | YOLOv8-Segmentation | SA8775P ADP | SA8775P | QNN | 10.118 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
60
- | YOLOv8-Segmentation | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 10.012 ms | 4 - 45 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
61
- | YOLOv8-Segmentation | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 9.586 ms | 5 - 47 MB | FP16 | NPU | Use Export Script |
62
- | YOLOv8-Segmentation | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 6.955 ms | 5 - 5 MB | FP16 | NPU | Use Export Script |
63
- | YOLOv8-Segmentation | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 7.702 ms | 17 - 17 MB | FP16 | NPU | [YOLOv8-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.onnx) |
64
 
65
 
66
 
67
 
68
  ## Installation
69
 
70
- This model can be installed as a Python package via pip.
71
 
 
72
  ```bash
73
- pip install "qai-hub-models[yolov8_seg]"
74
  ```
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
@@ -126,7 +125,7 @@ YOLOv8-Segmentation
126
  Device : Samsung Galaxy S23 (13)
127
  Runtime : TFLITE
128
  Estimated inference time (ms) : 6.5
129
- Estimated peak memory usage (MB): [4, 29]
130
  Total # Ops : 338
131
  Compute Unit(s) : NPU (338 ops)
132
  ```
@@ -153,7 +152,7 @@ from qai_hub_models.models.yolov8_seg import Model
153
  torch_model = Model.from_pretrained()
154
 
155
  # Device
156
- device = hub.Device("Samsung Galaxy S23")
157
 
158
  # Trace model
159
  input_shape = torch_model.get_input_spec()
@@ -245,7 +244,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
245
 
246
 
247
  ## License
248
- * The license for the original implementation of YOLOv8-Segmentation can be found [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).
 
249
  * The license for the compiled assets for on-device deployment can be found [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE)
250
 
251
 
 
36
 
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | YOLOv8-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 6.507 ms | 4 - 27 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
40
+ | YOLOv8-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 6.403 ms | 5 - 15 MB | FP16 | NPU | [YOLOv8-Segmentation.so](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.so) |
41
+ | YOLOv8-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 7.767 ms | 14 - 50 MB | FP16 | NPU | [YOLOv8-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.onnx) |
42
+ | YOLOv8-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 4.788 ms | 0 - 54 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
43
+ | YOLOv8-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 4.569 ms | 0 - 55 MB | FP16 | NPU | [YOLOv8-Segmentation.so](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.so) |
44
+ | YOLOv8-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 5.183 ms | 16 - 78 MB | FP16 | NPU | [YOLOv8-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.onnx) |
45
+ | YOLOv8-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 4.602 ms | 0 - 52 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
46
+ | YOLOv8-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 4.439 ms | 5 - 60 MB | FP16 | NPU | Use Export Script |
47
+ | YOLOv8-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 4.787 ms | 5 - 58 MB | FP16 | NPU | [YOLOv8-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.onnx) |
48
+ | YOLOv8-Segmentation | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 6.485 ms | 4 - 25 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
49
+ | YOLOv8-Segmentation | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 6.316 ms | 5 - 8 MB | FP16 | NPU | Use Export Script |
50
+ | YOLOv8-Segmentation | SA7255P ADP | SA7255P | TFLITE | 93.297 ms | 4 - 51 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
51
+ | YOLOv8-Segmentation | SA7255P ADP | SA7255P | QNN | 92.263 ms | 0 - 9 MB | FP16 | NPU | Use Export Script |
52
+ | YOLOv8-Segmentation | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 6.532 ms | 4 - 26 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
53
+ | YOLOv8-Segmentation | SA8255 (Proxy) | SA8255P Proxy | QNN | 6.294 ms | 5 - 8 MB | FP16 | NPU | Use Export Script |
54
+ | YOLOv8-Segmentation | SA8295P ADP | SA8295P | TFLITE | 11.454 ms | 4 - 42 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
55
+ | YOLOv8-Segmentation | SA8295P ADP | SA8295P | QNN | 11.015 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
56
+ | YOLOv8-Segmentation | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 6.539 ms | 4 - 27 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
57
+ | YOLOv8-Segmentation | SA8650 (Proxy) | SA8650P Proxy | QNN | 6.394 ms | 5 - 8 MB | FP16 | NPU | Use Export Script |
58
+ | YOLOv8-Segmentation | SA8775P ADP | SA8775P | TFLITE | 10.159 ms | 4 - 50 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
59
+ | YOLOv8-Segmentation | SA8775P ADP | SA8775P | QNN | 10.125 ms | 0 - 10 MB | FP16 | NPU | Use Export Script |
60
+ | YOLOv8-Segmentation | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 10.14 ms | 4 - 45 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
61
+ | YOLOv8-Segmentation | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 9.542 ms | 5 - 51 MB | FP16 | NPU | Use Export Script |
62
+ | YOLOv8-Segmentation | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 6.895 ms | 5 - 5 MB | FP16 | NPU | Use Export Script |
63
+ | YOLOv8-Segmentation | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 7.655 ms | 17 - 17 MB | FP16 | NPU | [YOLOv8-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.onnx) |
64
 
65
 
66
 
67
 
68
  ## Installation
69
 
 
70
 
71
+ Install the package via pip:
72
  ```bash
73
+ pip install "qai-hub-models[yolov8-seg]"
74
  ```
75
 
76
 
 
77
  ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
78
 
79
  Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
 
125
  Device : Samsung Galaxy S23 (13)
126
  Runtime : TFLITE
127
  Estimated inference time (ms) : 6.5
128
+ Estimated peak memory usage (MB): [4, 27]
129
  Total # Ops : 338
130
  Compute Unit(s) : NPU (338 ops)
131
  ```
 
152
  torch_model = Model.from_pretrained()
153
 
154
  # Device
155
+ device = hub.Device("Samsung Galaxy S24")
156
 
157
  # Trace model
158
  input_shape = torch_model.get_input_spec()
 
244
 
245
 
246
  ## License
247
+ * The license for the original implementation of YOLOv8-Segmentation can be found
248
+ [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).
249
  * The license for the compiled assets for on-device deployment can be found [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE)
250
 
251