Hugging Face's logo

qualcomm
/
YOLOv8-Segmentation

Image Segmentation
PyTorch
TF Lite
ONNX
real_time
android
Model card Files Community
bhushans commited on
Commit
54e88c5
·
verified ·
1 Parent(s): 7735b66

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +39 -25
README.md CHANGED
@@ -36,29 +36,27 @@ 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 | 6.58 ms | 4 - 7 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 | 6.435 ms | 5 - 19 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 | 7.637 ms | 12 - 20 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 | 4.674 ms | 4 - 118 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 | 4.601 ms | 5 - 61 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 | 5.063 ms | 16 - 135 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 | 4.509 ms | 3 - 74 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 | 4.372 ms | 5 - 55 MB | FP16 | NPU | Use Export Script |
47
- | YOLOv8-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 4.896 ms | 0 - 71 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 | 6.559 ms | 2 - 10 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 | 6.321 ms | 5 - 9 MB | FP16 | NPU | Use Export Script |
50
- | YOLOv8-Segmentation | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 6.473 ms | 0 - 175 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
51
- | YOLOv8-Segmentation | SA8255 (Proxy) | SA8255P Proxy | QNN | 6.295 ms | 5 - 11 MB | FP16 | NPU | Use Export Script |
52
- | YOLOv8-Segmentation | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 6.453 ms | 4 - 7 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
53
- | YOLOv8-Segmentation | SA8775 (Proxy) | SA8775P Proxy | QNN | 6.381 ms | 5 - 6 MB | FP16 | NPU | Use Export Script |
54
- | YOLOv8-Segmentation | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 6.424 ms | 1 - 3 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
55
- | YOLOv8-Segmentation | SA8650 (Proxy) | SA8650P Proxy | QNN | 6.278 ms | 5 - 6 MB | FP16 | NPU | Use Export Script |
56
- | YOLOv8-Segmentation | SA8295P ADP | SA8295P | TFLITE | 10.892 ms | 4 - 65 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
57
- | YOLOv8-Segmentation | SA8295P ADP | SA8295P | QNN | 10.437 ms | 0 - 5 MB | FP16 | NPU | Use Export Script |
58
- | YOLOv8-Segmentation | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 9.546 ms | 4 - 103 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
59
- | YOLOv8-Segmentation | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 9.162 ms | 5 - 45 MB | FP16 | NPU | Use Export Script |
60
- | YOLOv8-Segmentation | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 6.852 ms | 5 - 5 MB | FP16 | NPU | Use Export Script |
61
- | YOLOv8-Segmentation | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 7.643 ms | 17 - 17 MB | FP16 | NPU | [YOLOv8-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.onnx) |
62
 
63
 
64
 
@@ -123,8 +121,8 @@ Profiling Results
123
  YOLOv8-Segmentation
124
  Device : Samsung Galaxy S23 (13)
125
  Runtime : TFLITE
126
- Estimated inference time (ms) : 6.6
127
- Estimated peak memory usage (MB): [4, 7]
128
  Total # Ops : 338
129
  Compute Unit(s) : NPU (338 ops)
130
  ```
@@ -145,13 +143,29 @@ in memory using the `jit.trace` and then call the `submit_compile_job` API.
145
  import torch
146
 
147
  import qai_hub as hub
148
- from qai_hub_models.models.yolov8_seg import
149
 
150
  # Load the model
 
151
 
152
  # Device
153
  device = hub.Device("Samsung Galaxy S23")
154
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
155
 
156
  ```
157
 
 
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 | 6.517 ms | 4 - 22 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 | 6.409 ms | 5 - 14 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 | 7.65 ms | 12 - 30 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 | 4.706 ms | 4 - 56 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 | 4.587 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 | 5.004 ms | 0 - 118 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 | 4.751 ms | 4 - 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 | 4.372 ms | 5 - 55 MB | FP16 | NPU | Use Export Script |
47
+ | YOLOv8-Segmentation | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 6.534 ms | 4 - 26 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
48
+ | YOLOv8-Segmentation | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 6.294 ms | 5 - 6 MB | FP16 | NPU | Use Export Script |
49
+ | YOLOv8-Segmentation | SA7255P ADP | SA7255P | TFLITE | 93.433 ms | 4 - 50 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
50
+ | YOLOv8-Segmentation | SA7255P ADP | SA7255P | QNN | 92.33 ms | 0 - 5 MB | FP16 | NPU | Use Export Script |
51
+ | YOLOv8-Segmentation | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 6.446 ms | 4 - 27 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
52
+ | YOLOv8-Segmentation | SA8255 (Proxy) | SA8255P Proxy | QNN | 6.423 ms | 5 - 6 MB | FP16 | NPU | Use Export Script |
53
+ | YOLOv8-Segmentation | SA8295P ADP | SA8295P | TFLITE | 10.912 ms | 4 - 36 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
54
+ | YOLOv8-Segmentation | SA8295P ADP | SA8295P | QNN | 10.226 ms | 0 - 5 MB | FP16 | NPU | Use Export Script |
55
+ | YOLOv8-Segmentation | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 6.434 ms | 4 - 27 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
56
+ | YOLOv8-Segmentation | SA8650 (Proxy) | SA8650P Proxy | QNN | 6.446 ms | 5 - 8 MB | FP16 | NPU | Use Export Script |
57
+ | YOLOv8-Segmentation | SA8775P ADP | SA8775P | QNN | 10.151 ms | 1 - 7 MB | FP16 | NPU | Use Export Script |
58
+ | YOLOv8-Segmentation | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 9.761 ms | 4 - 42 MB | FP16 | NPU | [YOLOv8-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv8-Segmentation/blob/main/YOLOv8-Segmentation.tflite) |
59
+ | YOLOv8-Segmentation | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 9.567 ms | 5 - 43 MB | FP16 | NPU | Use Export Script |
 
 
60
 
61
 
62
 
 
121
  YOLOv8-Segmentation
122
  Device : Samsung Galaxy S23 (13)
123
  Runtime : TFLITE
124
+ Estimated inference time (ms) : 6.5
125
+ Estimated peak memory usage (MB): [4, 22]
126
  Total # Ops : 338
127
  Compute Unit(s) : NPU (338 ops)
128
  ```
 
143
  import torch
144
 
145
  import qai_hub as hub
146
+ from qai_hub_models.models.yolov8_seg import Model
147
 
148
  # Load the model
149
+ torch_model = Model.from_pretrained()
150
 
151
  # Device
152
  device = hub.Device("Samsung Galaxy S23")
153
 
154
+ # Trace model
155
+ input_shape = torch_model.get_input_spec()
156
+ sample_inputs = torch_model.sample_inputs()
157
+
158
+ pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
159
+
160
+ # Compile model on a specific device
161
+ compile_job = hub.submit_compile_job(
162
+ model=pt_model,
163
+ device=device,
164
+ input_specs=torch_model.get_input_spec(),
165
+ )
166
+
167
+ # Get target model to run on-device
168
+ target_model = compile_job.get_target_model()
169
 
170
  ```
171