--- library_name: pytorch license: other tags: - real_time - android pipeline_tag: object-detection --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolov8_det/web-assets/model_demo.png) # YOLOv8-Detection: Optimized for Mobile Deployment ## Real-time object detection optimized for mobile and edge by Ultralytics Ultralytics YOLOv8 is a machine learning model that predicts bounding boxes and classes of objects in an image. This model is an implementation of YOLOv8-Detection found [here](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/detect). This repository provides scripts to run YOLOv8-Detection on Qualcomm® devices. More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/yolov8_det). **WARNING**: The model assets are not readily available for download due to licensing restrictions. ### Model Details - **Model Type:** Model_use_case.object_detection - **Model Stats:** - Model checkpoint: YOLOv8-N - Input resolution: 640x640 - Number of parameters: 3.18M - Model size (float): 12.2 MB - Model size (w8a8): 3.25 MB - Model size (w8a16): 3.60 MB | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model |---|---|---|---|---|---|---|---|---| | YOLOv8-Detection | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 13.463 ms | 0 - 82 MB | NPU | -- | | YOLOv8-Detection | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 13.006 ms | 2 - 124 MB | NPU | -- | | YOLOv8-Detection | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 6.16 ms | 0 - 45 MB | NPU | -- | | YOLOv8-Detection | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 6.869 ms | 5 - 43 MB | NPU | -- | | YOLOv8-Detection | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 3.494 ms | 0 - 84 MB | NPU | -- | | YOLOv8-Detection | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 3.285 ms | 5 - 75 MB | NPU | -- | | YOLOv8-Detection | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 5.389 ms | 0 - 74 MB | NPU | -- | | YOLOv8-Detection | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 4.998 ms | 0 - 82 MB | NPU | -- | | YOLOv8-Detection | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 4.934 ms | 1 - 106 MB | NPU | -- | | YOLOv8-Detection | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 13.463 ms | 0 - 82 MB | NPU | -- | | YOLOv8-Detection | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 13.006 ms | 2 - 124 MB | NPU | -- | | YOLOv8-Detection | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 3.493 ms | 0 - 87 MB | NPU | -- | | YOLOv8-Detection | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 3.293 ms | 0 - 73 MB | NPU | -- | | YOLOv8-Detection | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 7.208 ms | 0 - 35 MB | NPU | -- | | YOLOv8-Detection | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 7.141 ms | 0 - 33 MB | NPU | -- | | YOLOv8-Detection | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 3.484 ms | 0 - 84 MB | NPU | -- | | YOLOv8-Detection | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 3.3 ms | 0 - 73 MB | NPU | -- | | YOLOv8-Detection | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 4.998 ms | 0 - 82 MB | NPU | -- | | YOLOv8-Detection | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 4.934 ms | 1 - 106 MB | NPU | -- | | YOLOv8-Detection | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 2.585 ms | 0 - 162 MB | NPU | -- | | YOLOv8-Detection | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 2.454 ms | 5 - 262 MB | NPU | -- | | YOLOv8-Detection | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.447 ms | 0 - 108 MB | NPU | -- | | YOLOv8-Detection | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 2.056 ms | 0 - 89 MB | NPU | -- | | YOLOv8-Detection | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 1.896 ms | 5 - 112 MB | NPU | -- | | YOLOv8-Detection | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 3.048 ms | 3 - 84 MB | NPU | -- | | YOLOv8-Detection | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 1.567 ms | 0 - 83 MB | NPU | -- | | YOLOv8-Detection | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 1.457 ms | 5 - 129 MB | NPU | -- | | YOLOv8-Detection | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 2.418 ms | 4 - 72 MB | NPU | -- | | YOLOv8-Detection | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.696 ms | 117 - 117 MB | NPU | -- | | YOLOv8-Detection | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 5.664 ms | 5 - 5 MB | NPU | -- | | YOLOv8-Detection | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 6.356 ms | 2 - 30 MB | NPU | -- | | YOLOv8-Detection | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 3.828 ms | 2 - 39 MB | NPU | -- | | YOLOv8-Detection | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 3.19 ms | 2 - 13 MB | NPU | -- | | YOLOv8-Detection | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 5.068 ms | 0 - 57 MB | NPU | -- | | YOLOv8-Detection | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 3.746 ms | 1 - 29 MB | NPU | -- | | YOLOv8-Detection | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 12.454 ms | 2 - 41 MB | NPU | -- | | YOLOv8-Detection | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | ONNX | 163.928 ms | 65 - 80 MB | CPU | -- | | YOLOv8-Detection | w8a16 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 135.474 ms | 61 - 65 MB | CPU | -- | | YOLOv8-Detection | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 6.356 ms | 2 - 30 MB | NPU | -- | | YOLOv8-Detection | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 3.195 ms | 2 - 12 MB | NPU | -- | | YOLOv8-Detection | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 4.424 ms | 0 - 34 MB | NPU | -- | | YOLOv8-Detection | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 3.198 ms | 2 - 11 MB | NPU | -- | | YOLOv8-Detection | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 3.746 ms | 1 - 29 MB | NPU | -- | | YOLOv8-Detection | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 2.107 ms | 2 - 38 MB | NPU | -- | | YOLOv8-Detection | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.065 ms | 2 - 105 MB | NPU | -- | | YOLOv8-Detection | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 1.458 ms | 2 - 40 MB | NPU | -- | | YOLOv8-Detection | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 2.402 ms | 0 - 77 MB | NPU | -- | | YOLOv8-Detection | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | QNN_DLC | 3.665 ms | 2 - 41 MB | NPU | -- | | YOLOv8-Detection | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | ONNX | 156.14 ms | 68 - 85 MB | CPU | -- | | YOLOv8-Detection | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 1.231 ms | 2 - 39 MB | NPU | -- | | YOLOv8-Detection | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 2.142 ms | 1 - 75 MB | NPU | -- | | YOLOv8-Detection | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.544 ms | 5 - 5 MB | NPU | -- | | YOLOv8-Detection | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 5.212 ms | 2 - 2 MB | NPU | -- | | YOLOv8-Detection | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 3.159 ms | 0 - 26 MB | NPU | -- | | YOLOv8-Detection | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 3.01 ms | 1 - 27 MB | NPU | -- | | YOLOv8-Detection | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 1.594 ms | 0 - 37 MB | NPU | -- | | YOLOv8-Detection | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 1.564 ms | 1 - 36 MB | NPU | -- | | YOLOv8-Detection | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1.436 ms | 0 - 5 MB | NPU | -- | | YOLOv8-Detection | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 1.322 ms | 0 - 15 MB | NPU | -- | | YOLOv8-Detection | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 2.192 ms | 0 - 45 MB | NPU | -- | | YOLOv8-Detection | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 1.847 ms | 0 - 26 MB | NPU | -- | | YOLOv8-Detection | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 1.695 ms | 1 - 27 MB | NPU | -- | | YOLOv8-Detection | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 3.591 ms | 0 - 32 MB | NPU | -- | | YOLOv8-Detection | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 4.43 ms | 0 - 34 MB | NPU | -- | | YOLOv8-Detection | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | ONNX | 40.939 ms | 19 - 36 MB | CPU | -- | | YOLOv8-Detection | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 44.624 ms | 3 - 12 MB | NPU | -- | | YOLOv8-Detection | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 36.284 ms | 21 - 28 MB | CPU | -- | | YOLOv8-Detection | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 3.159 ms | 0 - 26 MB | NPU | -- | | YOLOv8-Detection | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 3.01 ms | 1 - 27 MB | NPU | -- | | YOLOv8-Detection | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 1.42 ms | 0 - 15 MB | NPU | -- | | YOLOv8-Detection | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 1.319 ms | 1 - 16 MB | NPU | -- | | YOLOv8-Detection | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 2.231 ms | 0 - 32 MB | NPU | -- | | YOLOv8-Detection | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 2.065 ms | 1 - 33 MB | NPU | -- | | YOLOv8-Detection | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 1.436 ms | 0 - 15 MB | NPU | -- | | YOLOv8-Detection | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 1.309 ms | 0 - 14 MB | NPU | -- | | YOLOv8-Detection | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 1.847 ms | 0 - 26 MB | NPU | -- | | YOLOv8-Detection | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 1.695 ms | 1 - 27 MB | NPU | -- | | YOLOv8-Detection | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.944 ms | 0 - 43 MB | NPU | -- | | YOLOv8-Detection | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.907 ms | 1 - 37 MB | NPU | -- | | YOLOv8-Detection | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.469 ms | 0 - 144 MB | NPU | -- | | YOLOv8-Detection | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 0.733 ms | 0 - 30 MB | NPU | -- | | YOLOv8-Detection | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 0.646 ms | 1 - 31 MB | NPU | -- | | YOLOv8-Detection | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 1.088 ms | 0 - 81 MB | NPU | -- | | YOLOv8-Detection | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | TFLITE | 1.491 ms | 0 - 32 MB | NPU | -- | | YOLOv8-Detection | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | QNN_DLC | 1.417 ms | 1 - 32 MB | NPU | -- | | YOLOv8-Detection | w8a8 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | ONNX | 37.933 ms | 22 - 41 MB | CPU | -- | | YOLOv8-Detection | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 0.656 ms | 0 - 32 MB | NPU | -- | | YOLOv8-Detection | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 0.589 ms | 1 - 36 MB | NPU | -- | | YOLOv8-Detection | w8a8 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 0.95 ms | 1 - 84 MB | NPU | -- | | YOLOv8-Detection | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 1.525 ms | 3 - 3 MB | NPU | -- | | YOLOv8-Detection | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.17 ms | 2 - 2 MB | NPU | -- | | YOLOv8-Detection | w8a8_mixed_int16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 4.343 ms | 2 - 29 MB | NPU | -- | | YOLOv8-Detection | w8a8_mixed_int16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.041 ms | 2 - 13 MB | NPU | -- | | YOLOv8-Detection | w8a8_mixed_int16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 2.555 ms | 2 - 28 MB | NPU | -- | | YOLOv8-Detection | w8a8_mixed_int16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 4.343 ms | 2 - 29 MB | NPU | -- | | YOLOv8-Detection | w8a8_mixed_int16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 2.042 ms | 2 - 11 MB | NPU | -- | | YOLOv8-Detection | w8a8_mixed_int16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 2.049 ms | 2 - 11 MB | NPU | -- | | YOLOv8-Detection | w8a8_mixed_int16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 2.555 ms | 2 - 28 MB | NPU | -- | | YOLOv8-Detection | w8a8_mixed_int16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.37 ms | 2 - 39 MB | NPU | -- | | YOLOv8-Detection | w8a8_mixed_int16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 0.984 ms | 2 - 33 MB | NPU | -- | | YOLOv8-Detection | w8a8_mixed_int16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | QNN_DLC | 2.413 ms | 2 - 37 MB | NPU | -- | | YOLOv8-Detection | w8a8_mixed_int16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 0.825 ms | 2 - 38 MB | NPU | -- | | YOLOv8-Detection | w8a8_mixed_int16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 2.326 ms | 2 - 2 MB | NPU | -- | ## Installation Install the package via pip: ```bash # NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported. pip install "qai-hub-models[yolov8-det]" ``` ## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.com/) with your Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`. With this API token, you can configure your client to run models on the cloud hosted devices. ```bash qai-hub configure --api_token API_TOKEN ``` Navigate to [docs](https://workbench.aihub.qualcomm.com/docs/) for more information. ## Demo off target The package contains a simple end-to-end demo that downloads pre-trained weights and runs this model on a sample input. ```bash python -m qai_hub_models.models.yolov8_det.demo ``` The above demo runs a reference implementation of pre-processing, model inference, and post processing. **NOTE**: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above). ``` %run -m qai_hub_models.models.yolov8_det.demo ``` ### Run model on a cloud-hosted device In addition to the demo, you can also run the model on a cloud-hosted Qualcomm® device. This script does the following: * Performance check on-device on a cloud-hosted device * Downloads compiled assets that can be deployed on-device for Android. * Accuracy check between PyTorch and on-device outputs. ```bash python -m qai_hub_models.models.yolov8_det.export ``` ## How does this work? This [export script](https://aihub.qualcomm.com/models/yolov8_det/qai_hub_models/models/YOLOv8-Detection/export.py) leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) to optimize, validate, and deploy this model on-device. Lets go through each step below in detail: Step 1: **Compile model for on-device deployment** To compile a PyTorch model for on-device deployment, we first trace the model in memory using the `jit.trace` and then call the `submit_compile_job` API. ```python import torch import qai_hub as hub from qai_hub_models.models.yolov8_det import Model # Load the model torch_model = Model.from_pretrained() # Device device = hub.Device("Samsung Galaxy S25") # Trace model input_shape = torch_model.get_input_spec() sample_inputs = torch_model.sample_inputs() pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()]) # Compile model on a specific device compile_job = hub.submit_compile_job( model=pt_model, device=device, input_specs=torch_model.get_input_spec(), ) # Get target model to run on-device target_model = compile_job.get_target_model() ``` Step 2: **Performance profiling on cloud-hosted device** After compiling models from step 1. Models can be profiled model on-device using the `target_model`. Note that this scripts runs the model on a device automatically provisioned in the cloud. Once the job is submitted, you can navigate to a provided job URL to view a variety of on-device performance metrics. ```python profile_job = hub.submit_profile_job( model=target_model, device=device, ) ``` Step 3: **Verify on-device accuracy** To verify the accuracy of the model on-device, you can run on-device inference on sample input data on the same cloud hosted device. ```python input_data = torch_model.sample_inputs() inference_job = hub.submit_inference_job( model=target_model, device=device, inputs=input_data, ) on_device_output = inference_job.download_output_data() ``` With the output of the model, you can compute like PSNR, relative errors or spot check the output with expected output. **Note**: This on-device profiling and inference requires access to Qualcomm® AI Hub Workbench. [Sign up for access](https://myaccount.qualcomm.com/signup). ## Run demo on a cloud-hosted device You can also run the demo on-device. ```bash python -m qai_hub_models.models.yolov8_det.demo --eval-mode on-device ``` **NOTE**: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above). ``` %run -m qai_hub_models.models.yolov8_det.demo -- --eval-mode on-device ``` ## Deploying compiled model to Android The models can be deployed using multiple runtimes: - TensorFlow Lite (`.tflite` export): [This tutorial](https://www.tensorflow.org/lite/android/quickstart) provides a guide to deploy the .tflite model in an Android application. - QNN (`.so` export ): This [sample app](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html) provides instructions on how to use the `.so` shared library in an Android application. ## View on Qualcomm® AI Hub Get more details on YOLOv8-Detection's performance across various devices [here](https://aihub.qualcomm.com/models/yolov8_det). Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/) ## License * The license for the original implementation of YOLOv8-Detection can be found [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE). * The license for the compiled assets for on-device deployment can be found [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE) ## References * [Ultralytics YOLOv8 Docs: Object Detection](https://docs.ultralytics.com/tasks/detect/) * [Source Model Implementation](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/detect) ## Community * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI. * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).