---
library_name: pytorch
license: bsd-3-clause
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/v0.61.0/src/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 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_mixed/releases/v0.61.0/resnet_mixed-onnx-float.zip)
| ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_mixed/releases/v0.61.0/resnet_mixed-onnx-w8a16.zip)
| ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_mixed/releases/v0.61.0/resnet_mixed-onnx-w8a8.zip)
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_mixed/releases/v0.61.0/resnet_mixed-qnn_dlc-float.zip)
| QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_mixed/releases/v0.61.0/resnet_mixed-qnn_dlc-w8a16.zip)
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_mixed/releases/v0.61.0/resnet_mixed-qnn_dlc-w8a8.zip)
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_mixed/releases/v0.61.0/resnet_mixed-tflite-float.zip)
| TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_mixed/releases/v0.61.0/resnet_mixed-tflite-w8a8.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/v0.61.0/src/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/v0.61.0/src/qai_hub_models/models/resnet_mixed) for usage instructions.

## Model Details

**Model Type:** Model_use_case.video_classification

**Model Stats:**
- Input resolution: 112x112
- Model checkpoint: Kinetics-400
- Model size (float): 44.6 MB
- Model size (w8a16): 11.5 MB
- Number of parameters: 11.7M

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| ResNet-Mixed-Convolution | ONNX | float | Snapdragon® X2 Elite | 7.196 ms | 2 - 2 MB | NPU
| ResNet-Mixed-Convolution | ONNX | float | Snapdragon® X Elite | 13.7 ms | 22 - 22 MB | NPU
| ResNet-Mixed-Convolution | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 9.644 ms | 2 - 264 MB | NPU
| ResNet-Mixed-Convolution | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 25.826 ms | 3 - 225 MB | NPU
| ResNet-Mixed-Convolution | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 28.657 ms | 2 - 6 MB | NPU
| ResNet-Mixed-Convolution | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 13.112 ms | 0 - 28 MB | NPU
| ResNet-Mixed-Convolution | ONNX | float | Qualcomm® QCS8450 | 25.826 ms | 3 - 225 MB | NPU
| ResNet-Mixed-Convolution | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 25.726 ms | 2 - 5 MB | NPU
| ResNet-Mixed-Convolution | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 13.7 ms | 22 - 22 MB | NPU
| ResNet-Mixed-Convolution | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 7.861 ms | 0 - 209 MB | NPU
| ResNet-Mixed-Convolution | ONNX | float | Snapdragon® 8 Elite Mobile | 7.861 ms | 0 - 209 MB | NPU
| ResNet-Mixed-Convolution | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.818 ms | 2 - 216 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a16 | Snapdragon® X2 Elite | 4.668 ms | 1 - 1 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a16 | Snapdragon® X Elite | 8.95 ms | 12 - 12 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.423 ms | 1 - 242 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 12.459 ms | 1 - 242 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 51.16 ms | 1 - 4 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 9.567 ms | 1 - 5 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.606 ms | 0 - 25 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a16 | Qualcomm® QCS8450 | 12.459 ms | 1 - 242 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 8.311 ms | 1 - 4 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 8.95 ms | 12 - 12 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 172.088 ms | 1 - 200 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 15.19 ms | 1 - 197 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 5.201 ms | 1 - 186 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 5.201 ms | 1 - 186 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.658 ms | 0 - 194 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 15.19 ms | 1 - 197 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a8 | Snapdragon® X2 Elite | 2.332 ms | 2 - 2 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a8 | Snapdragon® X Elite | 4.907 ms | 12 - 12 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 3.398 ms | 0 - 217 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 6.93 ms | 1 - 217 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 25.07 ms | 1 - 3 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 24.689 ms | 3 - 6 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.736 ms | 0 - 16 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a8 | Qualcomm® QCS8450 | 6.93 ms | 1 - 217 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 4.552 ms | 1 - 3 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 4.907 ms | 12 - 12 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 93.684 ms | 1 - 189 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 8.014 ms | 1 - 177 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 2.816 ms | 0 - 184 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 2.816 ms | 0 - 184 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.908 ms | 0 - 177 MB | NPU
| ResNet-Mixed-Convolution | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 8.014 ms | 1 - 177 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Snapdragon® X2 Elite | 7.707 ms | 2 - 2 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Snapdragon® X Elite | 14.221 ms | 2 - 2 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 9.53 ms | 0 - 274 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 27.672 ms | 3 - 241 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 27.98 ms | 2 - 7 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 97.134 ms | 1 - 223 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 13.388 ms | 2 - 6 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® SA8775P | 25.21 ms | 1 - 224 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® SA8650P | 25.21 ms | 1 - 224 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® SA8255P | 25.21 ms | 1 - 224 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® QCS8450 | 27.672 ms | 3 - 241 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 25.518 ms | 2 - 6 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 14.221 ms | 2 - 2 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 7.639 ms | 0 - 224 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® SA7255P | 97.134 ms | 1 - 223 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Qualcomm® SA8295P | 26.858 ms | 2 - 197 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 7.639 ms | 0 - 224 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.906 ms | 2 - 234 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 5.443 ms | 1 - 1 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Snapdragon® X Elite | 10.185 ms | 1 - 1 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.775 ms | 1 - 242 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 13.318 ms | 1 - 244 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 51.693 ms | 1 - 3 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 54.387 ms | 4 - 12 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 30.068 ms | 1 - 190 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 9.43 ms | 1 - 3 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® SA8775P | 9.391 ms | 1 - 191 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® SA8650P | 9.391 ms | 1 - 191 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® SA8255P | 9.391 ms | 1 - 191 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 13.318 ms | 1 - 244 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 9.066 ms | 3 - 6 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 10.185 ms | 1 - 1 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 181.095 ms | 1 - 209 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 15.82 ms | 1 - 198 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 5.367 ms | 1 - 188 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® SA7255P | 30.068 ms | 1 - 190 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Qualcomm® SA8295P | 16.066 ms | 1 - 194 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 5.367 ms | 1 - 188 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 4.114 ms | 1 - 196 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 15.82 ms | 1 - 198 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 2.594 ms | 1 - 1 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Snapdragon® X Elite | 5.701 ms | 1 - 1 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 3.733 ms | 0 - 214 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 6.53 ms | 1 - 215 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 26.906 ms | 2 - 5 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 5.589 ms | 1 - 4 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 17.529 ms | 1 - 174 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.239 ms | 1 - 2 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Qualcomm® SA8775P | 5.352 ms | 1 - 175 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Qualcomm® SA8650P | 5.352 ms | 1 - 175 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Qualcomm® SA8255P | 5.352 ms | 1 - 175 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 6.53 ms | 1 - 215 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 5.519 ms | 0 - 2 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 5.701 ms | 1 - 1 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 98.576 ms | 1 - 201 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 7.888 ms | 1 - 176 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 2.972 ms | 0 - 175 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Qualcomm® SA7255P | 17.529 ms | 1 - 174 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Qualcomm® SA8295P | 9.386 ms | 1 - 177 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 2.972 ms | 0 - 175 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.9 ms | 1 - 193 MB | NPU
| ResNet-Mixed-Convolution | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 7.888 ms | 1 - 176 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 220.882 ms | 0 - 304 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 335.783 ms | 1 - 269 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 289.879 ms | 0 - 29 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 588.442 ms | 1 - 253 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 303.657 ms | 0 - 3 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | float | Qualcomm® SA8775P | 308.896 ms | 0 - 253 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | float | Qualcomm® SA8650P | 308.896 ms | 0 - 253 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | float | Qualcomm® SA8255P | 308.896 ms | 0 - 253 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | float | Qualcomm® QCS8450 | 335.783 ms | 1 - 269 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 312.784 ms | 0 - 28 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 211.173 ms | 0 - 254 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | float | Qualcomm® SA7255P | 588.442 ms | 1 - 253 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | float | Qualcomm® SA8295P | 352.458 ms | 0 - 235 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | float | Snapdragon® 8 Elite Mobile | 211.173 ms | 0 - 254 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 197.063 ms | 0 - 250 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 437.838 ms | 0 - 347 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 660.128 ms | 1 - 346 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 1777.221 ms | 695 - 1060 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 587.612 ms | 0 - 28 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1177.138 ms | 0 - 296 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 578.224 ms | 0 - 3 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Qualcomm® SA8775P | 600.359 ms | 0 - 295 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Qualcomm® SA8650P | 600.359 ms | 0 - 295 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Qualcomm® SA8255P | 600.359 ms | 0 - 295 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Qualcomm® QCS8450 | 660.128 ms | 1 - 346 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 600.471 ms | 0 - 27 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 1541.3 ms | 654 - 810 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1237.222 ms | 643 - 815 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 398.86 ms | 0 - 279 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Qualcomm® SA7255P | 1177.138 ms | 0 - 296 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Qualcomm® SA8295P | 655.374 ms | 0 - 297 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 398.86 ms | 0 - 279 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 434.782 ms | 0 - 344 MB | NPU
| ResNet-Mixed-Convolution | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1237.222 ms | 643 - 815 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).