Hugging Face's logo

qualcomm
/
Yolo-v7

Object Detection
PyTorch
TF Lite
ONNX
real_time
android
Model card Files Community
bhushans commited on
Commit
db48a38
·
verified ·
1 Parent(s): ee64879

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +40 -24
README.md CHANGED
@@ -35,29 +35,29 @@ More details on model performance across various devices, can be found
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
- | Yolo-v7 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 17.203 ms | 0 - 10 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
39
- | Yolo-v7 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 10.583 ms | 5 - 21 MB | FP16 | NPU | [Yolo-v7.so](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.so) |
40
- | Yolo-v7 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 12.221 ms | 0 - 13 MB | FP16 | NPU | [Yolo-v7.onnx](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.onnx) |
41
- | Yolo-v7 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 11.527 ms | 0 - 99 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
42
- | Yolo-v7 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 7.099 ms | 5 - 75 MB | FP16 | NPU | [Yolo-v7.so](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.so) |
43
- | Yolo-v7 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 7.984 ms | 6 - 124 MB | FP16 | NPU | [Yolo-v7.onnx](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.onnx) |
44
  | Yolo-v7 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 12.198 ms | 1 - 70 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
45
- | Yolo-v7 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 7.058 ms | 5 - 69 MB | FP16 | NPU | Use Export Script |
46
- | Yolo-v7 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 8.162 ms | 2 - 81 MB | FP16 | NPU | [Yolo-v7.onnx](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.onnx) |
47
- | Yolo-v7 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 17.066 ms | 1 - 4 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
48
- | Yolo-v7 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 10.342 ms | 5 - 6 MB | FP16 | NPU | Use Export Script |
49
- | Yolo-v7 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 17.232 ms | 0 - 2 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
50
- | Yolo-v7 | SA8255 (Proxy) | SA8255P Proxy | QNN | 10.441 ms | 5 - 6 MB | FP16 | NPU | Use Export Script |
51
- | Yolo-v7 | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 17.182 ms | 1 - 3 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
52
- | Yolo-v7 | SA8775 (Proxy) | SA8775P Proxy | QNN | 10.337 ms | 5 - 6 MB | FP16 | NPU | Use Export Script |
53
- | Yolo-v7 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 17.184 ms | 1 - 3 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
54
- | Yolo-v7 | SA8650 (Proxy) | SA8650P Proxy | QNN | 10.343 ms | 5 - 6 MB | FP16 | NPU | Use Export Script |
55
- | Yolo-v7 | SA8295P ADP | SA8295P | TFLITE | 21.595 ms | 1 - 73 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
56
- | Yolo-v7 | SA8295P ADP | SA8295P | QNN | 13.697 ms | 0 - 5 MB | FP16 | NPU | Use Export Script |
57
- | Yolo-v7 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 19.511 ms | 1 - 103 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
58
  | Yolo-v7 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 12.655 ms | 5 - 62 MB | FP16 | NPU | Use Export Script |
59
- | Yolo-v7 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 10.935 ms | 5 - 5 MB | FP16 | NPU | Use Export Script |
60
- | Yolo-v7 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 14.1 ms | 9 - 9 MB | FP16 | NPU | [Yolo-v7.onnx](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.onnx) |
61
 
62
 
63
 
@@ -122,8 +122,8 @@ Profiling Results
122
  Yolo-v7
123
  Device : Samsung Galaxy S23 (13)
124
  Runtime : TFLITE
125
- Estimated inference time (ms) : 17.2
126
- Estimated peak memory usage (MB): [0, 10]
127
  Total # Ops : 215
128
  Compute Unit(s) : NPU (215 ops)
129
  ```
@@ -144,13 +144,29 @@ in memory using the `jit.trace` and then call the `submit_compile_job` API.
144
  import torch
145
 
146
  import qai_hub as hub
147
- from qai_hub_models.models.yolov7 import
148
 
149
  # Load the model
 
150
 
151
  # Device
152
  device = hub.Device("Samsung Galaxy S23")
153
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
154
 
155
  ```
156
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | Yolo-v7 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 15.363 ms | 0 - 18 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
39
+ | Yolo-v7 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 10.64 ms | 5 - 21 MB | FP16 | NPU | [Yolo-v7.so](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.so) |
40
+ | Yolo-v7 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 12.262 ms | 0 - 12 MB | FP16 | NPU | [Yolo-v7.onnx](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.onnx) |
41
+ | Yolo-v7 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 10.281 ms | 1 - 46 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
42
+ | Yolo-v7 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 7.246 ms | 73 - 142 MB | FP16 | NPU | [Yolo-v7.so](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.so) |
43
+ | Yolo-v7 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 8.246 ms | 6 - 127 MB | FP16 | NPU | [Yolo-v7.onnx](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.onnx) |
44
  | Yolo-v7 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 12.198 ms | 1 - 70 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
45
+ | Yolo-v7 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 7.087 ms | 5 - 71 MB | FP16 | NPU | Use Export Script |
46
+ | Yolo-v7 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 8.166 ms | 6 - 89 MB | FP16 | NPU | [Yolo-v7.onnx](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.onnx) |
47
+ | Yolo-v7 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 15.228 ms | 1 - 18 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
48
+ | Yolo-v7 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 10.389 ms | 5 - 6 MB | FP16 | NPU | Use Export Script |
49
+ | Yolo-v7 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 15.315 ms | 1 - 16 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
50
+ | Yolo-v7 | SA8255 (Proxy) | SA8255P Proxy | QNN | 10.579 ms | 5 - 6 MB | FP16 | NPU | Use Export Script |
51
+ | Yolo-v7 | SA8295P ADP | SA8295P | TFLITE | 19.755 ms | 1 - 41 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
52
+ | Yolo-v7 | SA8295P ADP | SA8295P | QNN | 13.021 ms | 1 - 6 MB | FP16 | NPU | Use Export Script |
53
+ | Yolo-v7 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 15.333 ms | 1 - 21 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
54
+ | Yolo-v7 | SA8650 (Proxy) | SA8650P Proxy | QNN | 10.562 ms | 5 - 6 MB | FP16 | NPU | Use Export Script |
55
+ | Yolo-v7 | SA8775P ADP | SA8775P | TFLITE | 20.426 ms | 1 - 40 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
56
+ | Yolo-v7 | SA8775P ADP | SA8775P | QNN | 14.774 ms | 0 - 6 MB | FP16 | NPU | Use Export Script |
57
+ | Yolo-v7 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 17.644 ms | 1 - 46 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) |
58
  | Yolo-v7 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 12.655 ms | 5 - 62 MB | FP16 | NPU | Use Export Script |
59
+ | Yolo-v7 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 10.994 ms | 5 - 5 MB | FP16 | NPU | Use Export Script |
60
+ | Yolo-v7 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 14.522 ms | 9 - 9 MB | FP16 | NPU | [Yolo-v7.onnx](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.onnx) |
61
 
62
 
63
 
 
122
  Yolo-v7
123
  Device : Samsung Galaxy S23 (13)
124
  Runtime : TFLITE
125
+ Estimated inference time (ms) : 15.4
126
+ Estimated peak memory usage (MB): [0, 18]
127
  Total # Ops : 215
128
  Compute Unit(s) : NPU (215 ops)
129
  ```
 
144
  import torch
145
 
146
  import qai_hub as hub
147
+ from qai_hub_models.models.yolov7 import Model
148
 
149
  # Load the model
150
+ torch_model = Model.from_pretrained()
151
 
152
  # Device
153
  device = hub.Device("Samsung Galaxy S23")
154
 
155
+ # Trace model
156
+ input_shape = torch_model.get_input_spec()
157
+ sample_inputs = torch_model.sample_inputs()
158
+
159
+ pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
160
+
161
+ # Compile model on a specific device
162
+ compile_job = hub.submit_compile_job(
163
+ model=pt_model,
164
+ device=device,
165
+ input_specs=torch_model.get_input_spec(),
166
+ )
167
+
168
+ # Get target model to run on-device
169
+ target_model = compile_job.get_target_model()
170
 
171
  ```
172