Hugging Face's logo

qualcomm
/
ResNet-Mixed-Convolution

Video Classification
PyTorch
backbone
android
Model card Files
xet
 Community
1

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. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up 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 2.50, ONNX Runtime 1.27.1 Download
ONNX w8a16 Universal QAIRT 2.50, ONNX Runtime 1.27.1 Download
ONNX w8a8 Universal QAIRT 2.50, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.50 Download
QNN_DLC w8a16 Universal QAIRT 2.50 Download
QNN_DLC w8a8 Universal QAIRT 2.50 Download
TFLITE float Universal QAIRT 2.50 Download
TFLITE w8a8 Universal QAIRT 2.50 Download

For more device-specific assets and performance metrics, visit ResNet-Mixed-Convolution on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models 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 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® 8 Elite Gen 5 For Galaxy Mobile 5.738 ms 1 - 204 MB NPU
ResNet-Mixed-Convolution ONNX float Snapdragon® 8 Elite For Galaxy Mobile 7.689 ms 1 - 198 MB NPU
ResNet-Mixed-Convolution ONNX float Snapdragon® X2 Elite 7.1 ms 2 - 2 MB NPU
ResNet-Mixed-Convolution ONNX float Snapdragon® X Elite 13.618 ms 22 - 22 MB NPU
ResNet-Mixed-Convolution ONNX float Snapdragon® 8 Gen 3 Mobile 9.507 ms 2 - 255 MB NPU
ResNet-Mixed-Convolution ONNX float Snapdragon® 8 Gen 1 Mobile 24.027 ms 2 - 218 MB NPU
ResNet-Mixed-Convolution ONNX float Qualcomm® Dragonwing™ IQ-8275 28.138 ms 2 - 6 MB NPU
ResNet-Mixed-Convolution ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 13.045 ms 0 - 24 MB NPU
ResNet-Mixed-Convolution ONNX float Qualcomm® QCS8450 24.027 ms 2 - 218 MB NPU
ResNet-Mixed-Convolution ONNX float Qualcomm® Dragonwing™ IQ-9075 25.734 ms 2 - 6 MB NPU
ResNet-Mixed-Convolution ONNX float Qualcomm® Dragonwing™ IQ-X7181 13.618 ms 22 - 22 MB NPU
ResNet-Mixed-Convolution ONNX float Qualcomm® Dragonwing™ Q-8750 7.689 ms 1 - 198 MB NPU
ResNet-Mixed-Convolution ONNX w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 3.671 ms 0 - 192 MB NPU
ResNet-Mixed-Convolution ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 5.213 ms 1 - 180 MB NPU
ResNet-Mixed-Convolution ONNX w8a16 Snapdragon® X2 Elite 4.679 ms 1 - 1 MB NPU
ResNet-Mixed-Convolution ONNX w8a16 Snapdragon® X Elite 8.814 ms 11 - 11 MB NPU
ResNet-Mixed-Convolution ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 6.39 ms 1 - 236 MB NPU
ResNet-Mixed-Convolution ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 11.85 ms 1 - 238 MB NPU
ResNet-Mixed-Convolution ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 36.232 ms 1 - 4 MB NPU
ResNet-Mixed-Convolution ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 9.489 ms 1 - 5 MB NPU
ResNet-Mixed-Convolution ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 8.508 ms 0 - 15 MB NPU
ResNet-Mixed-Convolution ONNX w8a16 Qualcomm® QCS8450 11.85 ms 1 - 238 MB NPU
ResNet-Mixed-Convolution ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 8.312 ms 1 - 4 MB NPU
ResNet-Mixed-Convolution ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 8.814 ms 11 - 11 MB NPU
ResNet-Mixed-Convolution ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 175.086 ms 0 - 193 MB NPU
ResNet-Mixed-Convolution ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 16.552 ms 1 - 193 MB NPU
ResNet-Mixed-Convolution ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 5.213 ms 1 - 180 MB NPU
ResNet-Mixed-Convolution ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 16.552 ms 1 - 193 MB NPU
ResNet-Mixed-Convolution ONNX w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.86 ms 0 - 175 MB NPU
ResNet-Mixed-Convolution ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 2.737 ms 0 - 169 MB NPU
ResNet-Mixed-Convolution ONNX w8a8 Snapdragon® X2 Elite 2.312 ms 2 - 2 MB NPU
ResNet-Mixed-Convolution ONNX w8a8 Snapdragon® X Elite 4.722 ms 12 - 12 MB NPU
ResNet-Mixed-Convolution ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 3.267 ms 0 - 211 MB NPU
ResNet-Mixed-Convolution ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 6.053 ms 1 - 209 MB NPU
ResNet-Mixed-Convolution ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 18.585 ms 1 - 4 MB NPU
ResNet-Mixed-Convolution ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 4.993 ms 1 - 5 MB NPU
ResNet-Mixed-Convolution ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.561 ms 0 - 124 MB NPU
ResNet-Mixed-Convolution ONNX w8a8 Qualcomm® QCS8450 6.053 ms 1 - 209 MB NPU
ResNet-Mixed-Convolution ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 4.441 ms 1 - 4 MB NPU
ResNet-Mixed-Convolution ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 4.722 ms 12 - 12 MB NPU
ResNet-Mixed-Convolution ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 93.242 ms 3 - 184 MB NPU
ResNet-Mixed-Convolution ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 8.022 ms 1 - 176 MB NPU
ResNet-Mixed-Convolution ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 2.737 ms 0 - 169 MB NPU
ResNet-Mixed-Convolution ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 8.022 ms 1 - 176 MB NPU
ResNet-Mixed-Convolution QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 5.865 ms 2 - 207 MB NPU
ResNet-Mixed-Convolution QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 7.735 ms 0 - 200 MB NPU
ResNet-Mixed-Convolution QNN_DLC float Snapdragon® X2 Elite 7.77 ms 2 - 2 MB NPU
ResNet-Mixed-Convolution QNN_DLC float Snapdragon® X Elite 13.922 ms 2 - 2 MB NPU
ResNet-Mixed-Convolution QNN_DLC float Snapdragon® 8 Gen 3 Mobile 9.526 ms 0 - 253 MB NPU
ResNet-Mixed-Convolution QNN_DLC float Snapdragon® 8 Gen 1 Mobile 24.31 ms 2 - 217 MB NPU
ResNet-Mixed-Convolution QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 28.323 ms 2 - 7 MB NPU
ResNet-Mixed-Convolution QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 13.265 ms 2 - 4 MB NPU
ResNet-Mixed-Convolution QNN_DLC float Qualcomm® SA8775P 25.151 ms 1 - 200 MB NPU
ResNet-Mixed-Convolution QNN_DLC float Qualcomm® SA8650P 25.151 ms 1 - 200 MB NPU
ResNet-Mixed-Convolution QNN_DLC float Qualcomm® SA8255P 25.151 ms 1 - 200 MB NPU
ResNet-Mixed-Convolution QNN_DLC float Qualcomm® QCS8450 24.31 ms 2 - 217 MB NPU
ResNet-Mixed-Convolution QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 25.493 ms 2 - 7 MB NPU
ResNet-Mixed-Convolution QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 13.922 ms 2 - 2 MB NPU
ResNet-Mixed-Convolution QNN_DLC float Qualcomm® Dragonwing™ Q-8750 7.735 ms 0 - 200 MB NPU
ResNet-Mixed-Convolution QNN_DLC float Qualcomm® SA7255P 97.483 ms 1 - 200 MB NPU
ResNet-Mixed-Convolution QNN_DLC float Qualcomm® SA8295P 26.963 ms 0 - 173 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 3.798 ms 1 - 186 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 5.465 ms 1 - 177 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Snapdragon® X2 Elite 5.294 ms 1 - 1 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Snapdragon® X Elite 9.258 ms 1 - 1 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 6.477 ms 0 - 230 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 12.075 ms 1 - 232 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 37.226 ms 1 - 4 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 9.582 ms 1 - 5 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 8.617 ms 1 - 3 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Qualcomm® SA8775P 8.61 ms 1 - 181 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Qualcomm® SA8650P 8.61 ms 1 - 181 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Qualcomm® SA8255P 8.61 ms 1 - 181 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Qualcomm® QCS8450 12.075 ms 1 - 232 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 8.334 ms 1 - 4 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 9.258 ms 1 - 1 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 174.258 ms 1 - 191 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 16.784 ms 1 - 190 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 5.465 ms 1 - 177 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Qualcomm® SA7255P 29.978 ms 1 - 180 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Qualcomm® SA8295P 15.762 ms 1 - 186 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 16.784 ms 1 - 190 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.904 ms 1 - 171 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 2.752 ms 0 - 171 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Snapdragon® X2 Elite 2.676 ms 1 - 1 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Snapdragon® X Elite 5.09 ms 1 - 1 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 3.319 ms 0 - 208 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 6.338 ms 1 - 208 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 18.485 ms 3 - 5 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 5.054 ms 1 - 4 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.643 ms 1 - 2 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Qualcomm® SA8775P 4.686 ms 1 - 166 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Qualcomm® SA8650P 4.686 ms 1 - 166 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Qualcomm® SA8255P 4.686 ms 1 - 166 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Qualcomm® QCS8450 6.338 ms 1 - 208 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 4.516 ms 0 - 3 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 5.09 ms 1 - 1 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 90.294 ms 1 - 181 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 7.899 ms 1 - 166 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 2.752 ms 0 - 171 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Qualcomm® SA7255P 16.433 ms 1 - 166 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Qualcomm® SA8295P 8.54 ms 1 - 170 MB NPU
ResNet-Mixed-Convolution QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 7.899 ms 1 - 166 MB NPU
ResNet-Mixed-Convolution TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 180.172 ms 0 - 234 MB NPU
ResNet-Mixed-Convolution TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 189.335 ms 0 - 231 MB NPU
ResNet-Mixed-Convolution TFLITE float Snapdragon® 8 Gen 3 Mobile 201.929 ms 0 - 282 MB NPU
ResNet-Mixed-Convolution TFLITE float Snapdragon® 8 Gen 1 Mobile 303.531 ms 0 - 259 MB NPU
ResNet-Mixed-Convolution TFLITE float Qualcomm® Dragonwing™ IQ-8275 255.843 ms 0 - 30 MB NPU
ResNet-Mixed-Convolution TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 255.088 ms 0 - 3 MB NPU
ResNet-Mixed-Convolution TFLITE float Qualcomm® SA8775P 258.854 ms 0 - 228 MB NPU
ResNet-Mixed-Convolution TFLITE float Qualcomm® SA8650P 258.854 ms 0 - 228 MB NPU
ResNet-Mixed-Convolution TFLITE float Qualcomm® SA8255P 258.854 ms 0 - 228 MB NPU
ResNet-Mixed-Convolution TFLITE float Qualcomm® QCS8450 303.531 ms 0 - 259 MB NPU
ResNet-Mixed-Convolution TFLITE float Qualcomm® Dragonwing™ IQ-9075 263.913 ms 0 - 29 MB NPU
ResNet-Mixed-Convolution TFLITE float Qualcomm® Dragonwing™ Q-8750 189.335 ms 0 - 231 MB NPU
ResNet-Mixed-Convolution TFLITE float Qualcomm® SA7255P 501.821 ms 0 - 226 MB NPU
ResNet-Mixed-Convolution TFLITE float Qualcomm® SA8295P 309.555 ms 0 - 213 MB NPU
ResNet-Mixed-Convolution TFLITE w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 358.895 ms 0 - 318 MB NPU
ResNet-Mixed-Convolution TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 349.591 ms 0 - 257 MB NPU
ResNet-Mixed-Convolution TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 413.541 ms 0 - 334 MB NPU
ResNet-Mixed-Convolution TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 671.57 ms 2 - 330 MB NPU
ResNet-Mixed-Convolution TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 1769.212 ms 693 - 1059 MB NPU
ResNet-Mixed-Convolution TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 550.841 ms 0 - 29 MB NPU
ResNet-Mixed-Convolution TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 547.386 ms 0 - 2 MB NPU
ResNet-Mixed-Convolution TFLITE w8a8 Qualcomm® SA8775P 609.107 ms 0 - 279 MB NPU
ResNet-Mixed-Convolution TFLITE w8a8 Qualcomm® SA8650P 609.107 ms 0 - 279 MB NPU
ResNet-Mixed-Convolution TFLITE w8a8 Qualcomm® SA8255P 609.107 ms 0 - 279 MB NPU
ResNet-Mixed-Convolution TFLITE w8a8 Qualcomm® QCS8450 671.57 ms 2 - 330 MB NPU
ResNet-Mixed-Convolution TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 611.298 ms 0 - 28 MB NPU
ResNet-Mixed-Convolution TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 1536.734 ms 654 - 805 MB NPU
ResNet-Mixed-Convolution TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 1232.249 ms 668 - 843 MB NPU
ResNet-Mixed-Convolution TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 349.591 ms 0 - 257 MB NPU
ResNet-Mixed-Convolution TFLITE w8a8 Qualcomm® SA7255P 1189.445 ms 678 - 693 MB CPU
ResNet-Mixed-Convolution TFLITE w8a8 Qualcomm® SA8295P 621.284 ms 0 - 282 MB NPU
ResNet-Mixed-Convolution TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 1232.249 ms 668 - 843 MB NPU

License

  • The license for the original implementation of ResNet-Mixed-Convolution can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Video Classification
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/ResNet-Mixed-Convolution