--- library_name: pytorch license: other tags: - backbone - android pipeline_tag: video-classification --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_mixed/web-assets/model_demo.png) # ResNet-Mixed-Convolution: Optimized for Qualcomm Devices ResNet Mixed Convolutions is a network with a mixture of 2D and 3D convolutions used for video understanding. This is based on the implementation of ResNet-Mixed-Convolution found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/video/resnet.py). This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/resnet_mixed) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary). Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device. ## Getting Started There are two ways to deploy this model on your device: ### Option 1: Download Pre-Exported Models Below are pre-exported model assets ready for deployment. | Runtime | Precision | Chipset | SDK Versions | Download | |---|---|---|---|---| | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_mixed/releases/v0.50.0/resnet_mixed-onnx-float.zip) | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_mixed/releases/v0.50.0/resnet_mixed-onnx-w8a16.zip) | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_mixed/releases/v0.50.0/resnet_mixed-qnn_dlc-float.zip) | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_mixed/releases/v0.50.0/resnet_mixed-qnn_dlc-w8a16.zip) | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_mixed/releases/v0.50.0/resnet_mixed-tflite-float.zip) For more device-specific assets and performance metrics, visit **[ResNet-Mixed-Convolution on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/resnet_mixed)**. ### Option 2: Export with Custom Configurations Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/resnet_mixed) Python library to compile and export the model with your own: - Custom weights (e.g., fine-tuned checkpoints) - Custom input shapes - Target device and runtime configurations This option is ideal if you need to customize the model beyond the default configuration provided here. See our repository for [ResNet-Mixed-Convolution on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/resnet_mixed) for usage instructions. ## Model Details **Model Type:** Model_use_case.video_classification **Model Stats:** - Model checkpoint: Kinetics-400 - Input resolution: 112x112 - Number of parameters: 11.7M - Model size (float): 44.6 MB - Model size (w8a16): 11.5 MB ## Performance Summary | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |---|---|---|---|---|---|--- | ResNet-Mixed-Convolution | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.557 ms | 2 - 220 MB | NPU | ResNet-Mixed-Convolution | ONNX | float | Snapdragon® X2 Elite | 7.104 ms | 22 - 22 MB | NPU | ResNet-Mixed-Convolution | ONNX | float | Snapdragon® X Elite | 13.826 ms | 22 - 22 MB | NPU | ResNet-Mixed-Convolution | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 9.597 ms | 2 - 267 MB | NPU | ResNet-Mixed-Convolution | ONNX | float | Qualcomm® QCS8550 (Proxy) | 13.313 ms | 0 - 28 MB | NPU | ResNet-Mixed-Convolution | ONNX | float | Qualcomm® QCS9075 | 26.335 ms | 2 - 5 MB | NPU | ResNet-Mixed-Convolution | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.83 ms | 1 - 217 MB | NPU | ResNet-Mixed-Convolution | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.513 ms | 0 - 191 MB | NPU | ResNet-Mixed-Convolution | ONNX | w8a16 | Snapdragon® X2 Elite | 4.644 ms | 12 - 12 MB | NPU | ResNet-Mixed-Convolution | ONNX | w8a16 | Snapdragon® X Elite | 9.059 ms | 11 - 11 MB | NPU | ResNet-Mixed-Convolution | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.387 ms | 1 - 257 MB | NPU | ResNet-Mixed-Convolution | ONNX | w8a16 | Qualcomm® QCS6490 | 1736.807 ms | 51 - 61 MB | CPU | ResNet-Mixed-Convolution | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 8.506 ms | 1 - 5 MB | NPU | ResNet-Mixed-Convolution | ONNX | w8a16 | Qualcomm® QCS9075 | 9.041 ms | 1 - 4 MB | NPU | ResNet-Mixed-Convolution | ONNX | w8a16 | Qualcomm® QCM6690 | 892.043 ms | 105 - 112 MB | CPU | ResNet-Mixed-Convolution | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 5.231 ms | 1 - 193 MB | NPU | ResNet-Mixed-Convolution | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 872.531 ms | 112 - 119 MB | CPU | ResNet-Mixed-Convolution | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.738 ms | 2 - 233 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | float | Snapdragon® X2 Elite | 7.615 ms | 2 - 2 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | float | Snapdragon® X Elite | 13.988 ms | 2 - 2 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 9.558 ms | 0 - 285 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 97.148 ms | 1 - 224 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 13.187 ms | 2 - 4 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® SA8775P | 115.885 ms | 1 - 223 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® QCS9075 | 27.497 ms | 2 - 6 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 27.578 ms | 0 - 244 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® SA7255P | 97.148 ms | 1 - 224 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® SA8295P | 26.783 ms | 0 - 194 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.641 ms | 2 - 227 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 4.009 ms | 0 - 187 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 5.38 ms | 1 - 1 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Snapdragon® X Elite | 9.832 ms | 1 - 1 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.636 ms | 1 - 257 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 37.476 ms | 1 - 4 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 29.739 ms | 1 - 190 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 9.17 ms | 1 - 185 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® SA8775P | 9.399 ms | 1 - 191 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 10.395 ms | 3 - 6 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 184.761 ms | 1 - 208 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 14.18 ms | 1 - 256 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® SA7255P | 29.739 ms | 1 - 190 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® SA8295P | 16.314 ms | 1 - 192 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 5.265 ms | 1 - 187 MB | NPU | ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 15.773 ms | 1 - 197 MB | NPU | ResNet-Mixed-Convolution | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 198.433 ms | 0 - 251 MB | NPU | ResNet-Mixed-Convolution | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 220.315 ms | 0 - 313 MB | NPU | ResNet-Mixed-Convolution | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 585.071 ms | 0 - 249 MB | NPU | ResNet-Mixed-Convolution | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 309.507 ms | 0 - 3 MB | NPU | ResNet-Mixed-Convolution | TFLITE | float | Qualcomm® SA8775P | 298.104 ms | 0 - 249 MB | NPU | ResNet-Mixed-Convolution | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 336.74 ms | 0 - 280 MB | NPU | ResNet-Mixed-Convolution | TFLITE | float | Qualcomm® SA7255P | 585.071 ms | 0 - 249 MB | NPU | ResNet-Mixed-Convolution | TFLITE | float | Qualcomm® SA8295P | 362.965 ms | 0 - 232 MB | NPU | ResNet-Mixed-Convolution | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 203.914 ms | 0 - 246 MB | NPU ## License * The license for the original implementation of ResNet-Mixed-Convolution can be found [here](https://github.com/pytorch/vision/blob/main/LICENSE). ## References * [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://arxiv.org/abs/1711.11248) * [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/video/resnet.py) ## 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).