Hugging Face's logo

qualcomm
/
YOLOv11-Segmentation

Image Segmentation
PyTorch
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
845a98b
·
verified ·
1 Parent(s): b22fe06

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +20 -20
README.md CHANGED
@@ -36,34 +36,33 @@ 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
- | YOLOv11-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 6.668 ms | 4 - 32 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
40
- | YOLOv11-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 105.674 ms | 95 - 109 MB | FP32 | CPU | [YOLOv11-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.onnx) |
41
- | YOLOv11-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 4.885 ms | 0 - 54 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
42
- | YOLOv11-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 82.294 ms | 99 - 125 MB | FP32 | CPU | [YOLOv11-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.onnx) |
43
- | YOLOv11-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 4.706 ms | 3 - 56 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
44
- | YOLOv11-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 88.768 ms | 99 - 115 MB | FP32 | CPU | [YOLOv11-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.onnx) |
45
- | YOLOv11-Segmentation | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 6.738 ms | 4 - 31 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
46
- | YOLOv11-Segmentation | SA7255P ADP | SA7255P | TFLITE | 81.264 ms | 4 - 52 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
47
- | YOLOv11-Segmentation | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 6.741 ms | 4 - 23 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
48
- | YOLOv11-Segmentation | SA8295P ADP | SA8295P | TFLITE | 12.223 ms | 4 - 43 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
49
- | YOLOv11-Segmentation | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 6.686 ms | 4 - 23 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
50
- | YOLOv11-Segmentation | SA8775P ADP | SA8775P | TFLITE | 10.061 ms | 4 - 52 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
51
- | YOLOv11-Segmentation | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 10.691 ms | 4 - 43 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
52
- | YOLOv11-Segmentation | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 31.975 ms | 116 - 116 MB | FP32 | CPU | [YOLOv11-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.onnx) |
53
 
54
 
55
 
56
 
57
  ## Installation
58
 
59
- This model can be installed as a Python package via pip.
60
 
 
61
  ```bash
62
- pip install "qai-hub-models[yolov11_seg]"
63
  ```
64
 
65
 
66
-
67
  ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
68
 
69
  Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
@@ -115,7 +114,7 @@ YOLOv11-Segmentation
115
  Device : Samsung Galaxy S23 (13)
116
  Runtime : TFLITE
117
  Estimated inference time (ms) : 6.7
118
- Estimated peak memory usage (MB): [4, 32]
119
  Total # Ops : 429
120
  Compute Unit(s) : NPU (429 ops)
121
  ```
@@ -142,7 +141,7 @@ from qai_hub_models.models.yolov11_seg import Model
142
  torch_model = Model.from_pretrained()
143
 
144
  # Device
145
- device = hub.Device("Samsung Galaxy S23")
146
 
147
  # Trace model
148
  input_shape = torch_model.get_input_spec()
@@ -234,7 +233,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
234
 
235
 
236
  ## License
237
- * The license for the original implementation of YOLOv11-Segmentation can be found [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).
 
238
  * The license for the compiled assets for on-device deployment can be found [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE)
239
 
240
 
 
36
 
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | YOLOv11-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 6.693 ms | 4 - 23 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
40
+ | YOLOv11-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 123.821 ms | 95 - 109 MB | FP32 | CPU | [YOLOv11-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.onnx) |
41
+ | YOLOv11-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 4.927 ms | 4 - 61 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
42
+ | YOLOv11-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 83.391 ms | 101 - 129 MB | FP32 | CPU | [YOLOv11-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.onnx) |
43
+ | YOLOv11-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 4.723 ms | 4 - 57 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
44
+ | YOLOv11-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 88.892 ms | 100 - 115 MB | FP32 | CPU | [YOLOv11-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.onnx) |
45
+ | YOLOv11-Segmentation | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 6.725 ms | 4 - 27 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
46
+ | YOLOv11-Segmentation | SA7255P ADP | SA7255P | TFLITE | 81.221 ms | 4 - 51 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
47
+ | YOLOv11-Segmentation | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 6.681 ms | 4 - 27 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
48
+ | YOLOv11-Segmentation | SA8295P ADP | SA8295P | TFLITE | 12.22 ms | 4 - 42 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
49
+ | YOLOv11-Segmentation | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 6.739 ms | 4 - 22 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
50
+ | YOLOv11-Segmentation | SA8775P ADP | SA8775P | TFLITE | 10.058 ms | 4 - 52 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
51
+ | YOLOv11-Segmentation | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 10.725 ms | 4 - 43 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
52
+ | YOLOv11-Segmentation | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 32.261 ms | 117 - 117 MB | FP32 | CPU | [YOLOv11-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.onnx) |
53
 
54
 
55
 
56
 
57
  ## Installation
58
 
 
59
 
60
+ Install the package via pip:
61
  ```bash
62
+ pip install "qai-hub-models[yolov11-seg]"
63
  ```
64
 
65
 
 
66
  ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
67
 
68
  Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
 
114
  Device : Samsung Galaxy S23 (13)
115
  Runtime : TFLITE
116
  Estimated inference time (ms) : 6.7
117
+ Estimated peak memory usage (MB): [4, 23]
118
  Total # Ops : 429
119
  Compute Unit(s) : NPU (429 ops)
120
  ```
 
141
  torch_model = Model.from_pretrained()
142
 
143
  # Device
144
+ device = hub.Device("Samsung Galaxy S24")
145
 
146
  # Trace model
147
  input_shape = torch_model.get_input_spec()
 
233
 
234
 
235
  ## License
236
+ * The license for the original implementation of YOLOv11-Segmentation can be found
237
+ [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).
238
  * The license for the compiled assets for on-device deployment can be found [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE)
239
 
240