Hugging Face's logo

qualcomm
/
ResNet-Mixed-Convolution

Video Classification
PyTorch
LiteRT
backbone
android
Model card Files
xet
Community

ResNet-Mixed-Convolution: Optimized for Mobile Deployment

Sports and human action recognition in videos

ResNet Mixed Convolutions is a network with a mixture of 2D and 3D convolutions used for video understanding.

This model is an implementation of ResNet-Mixed-Convolution found here.

This repository provides scripts to run ResNet-Mixed-Convolution on Qualcomm® devices. More details on model performance across various devices, can be found here.

Model Details

  • Model Type: Model_use_case.video_classification
  • Model Stats:
    • Model checkpoint: Kinectics-400
    • Input resolution: 112x112
    • Number of parameters: 11.7M
    • Model size (float): 44.6 MB
    • Model size (w8a16): 11.5 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
ResNet-Mixed-Convolution float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 612.416 ms 0 - 73 MB NPU ResNet-Mixed-Convolution.tflite
ResNet-Mixed-Convolution float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 97.044 ms 0 - 63 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 336.064 ms 0 - 62 MB NPU ResNet-Mixed-Convolution.tflite
ResNet-Mixed-Convolution float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 28.329 ms 2 - 62 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 319.847 ms 0 - 23 MB NPU ResNet-Mixed-Convolution.tflite
ResNet-Mixed-Convolution float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 13.171 ms 2 - 25 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 13.83 ms 0 - 76 MB NPU ResNet-Mixed-Convolution.onnx.zip
ResNet-Mixed-Convolution float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 298.059 ms 0 - 71 MB NPU ResNet-Mixed-Convolution.tflite
ResNet-Mixed-Convolution float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 25.093 ms 0 - 65 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution float SA7255P ADP Qualcomm® SA7255P TFLITE 612.416 ms 0 - 73 MB NPU ResNet-Mixed-Convolution.tflite
ResNet-Mixed-Convolution float SA7255P ADP Qualcomm® SA7255P QNN_DLC 97.044 ms 0 - 63 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 310.851 ms 0 - 21 MB NPU ResNet-Mixed-Convolution.tflite
ResNet-Mixed-Convolution float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 13.095 ms 2 - 26 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution float SA8295P ADP Qualcomm® SA8295P TFLITE 347.435 ms 0 - 49 MB NPU ResNet-Mixed-Convolution.tflite
ResNet-Mixed-Convolution float SA8295P ADP Qualcomm® SA8295P QNN_DLC 26.649 ms 0 - 51 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 316.122 ms 0 - 24 MB NPU ResNet-Mixed-Convolution.tflite
ResNet-Mixed-Convolution float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 13.149 ms 2 - 30 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution float SA8775P ADP Qualcomm® SA8775P TFLITE 298.059 ms 0 - 71 MB NPU ResNet-Mixed-Convolution.tflite
ResNet-Mixed-Convolution float SA8775P ADP Qualcomm® SA8775P QNN_DLC 25.093 ms 0 - 65 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 216.567 ms 0 - 76 MB NPU ResNet-Mixed-Convolution.tflite
ResNet-Mixed-Convolution float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 9.399 ms 2 - 73 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 10.007 ms 0 - 91 MB NPU ResNet-Mixed-Convolution.onnx.zip
ResNet-Mixed-Convolution float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 212.785 ms 0 - 67 MB NPU ResNet-Mixed-Convolution.tflite
ResNet-Mixed-Convolution float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 7.712 ms 0 - 69 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 8.199 ms 0 - 76 MB NPU ResNet-Mixed-Convolution.onnx.zip
ResNet-Mixed-Convolution float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 195.743 ms 0 - 79 MB NPU ResNet-Mixed-Convolution.tflite
ResNet-Mixed-Convolution float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 5.682 ms 2 - 73 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 5.88 ms 2 - 78 MB NPU ResNet-Mixed-Convolution.onnx.zip
ResNet-Mixed-Convolution float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 13.873 ms 268 - 268 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 14.079 ms 22 - 22 MB NPU ResNet-Mixed-Convolution.onnx.zip
ResNet-Mixed-Convolution w8a16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 27.604 ms 1 - 45 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution w8a16 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 12.735 ms 1 - 60 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 8.42 ms 1 - 18 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 7.556 ms 0 - 40 MB NPU ResNet-Mixed-Convolution.onnx.zip
ResNet-Mixed-Convolution w8a16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 8.959 ms 1 - 46 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_DLC 55.232 ms 1 - 66 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) ONNX 767.841 ms 99 - 111 MB CPU ResNet-Mixed-Convolution.onnx.zip
ResNet-Mixed-Convolution w8a16 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) ONNX 733.015 ms 91 - 112 MB CPU ResNet-Mixed-Convolution.onnx.zip
ResNet-Mixed-Convolution w8a16 SA7255P ADP Qualcomm® SA7255P QNN_DLC 27.604 ms 1 - 45 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution w8a16 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 8.425 ms 0 - 27 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution w8a16 SA8295P ADP Qualcomm® SA8295P QNN_DLC 15.129 ms 1 - 47 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution w8a16 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 8.453 ms 0 - 29 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution w8a16 SA8775P ADP Qualcomm® SA8775P QNN_DLC 8.959 ms 1 - 46 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 6.095 ms 1 - 63 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 5.764 ms 1 - 65 MB NPU ResNet-Mixed-Convolution.onnx.zip
ResNet-Mixed-Convolution w8a16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 4.98 ms 1 - 48 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution w8a16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 4.751 ms 1 - 46 MB NPU ResNet-Mixed-Convolution.onnx.zip
ResNet-Mixed-Convolution w8a16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 3.585 ms 1 - 46 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution w8a16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 3.583 ms 1 - 47 MB NPU ResNet-Mixed-Convolution.onnx.zip
ResNet-Mixed-Convolution w8a16 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 8.954 ms 31 - 31 MB NPU ResNet-Mixed-Convolution.dlc
ResNet-Mixed-Convolution w8a16 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 7.987 ms 12 - 12 MB NPU ResNet-Mixed-Convolution.onnx.zip

Installation

Install the package via pip:

pip install "qai-hub-models[resnet-mixed]"

Configure Qualcomm® AI Hub to run this model on a cloud-hosted device

Sign-in to Qualcomm® AI Hub 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.

qai-hub configure --api_token API_TOKEN

Navigate to 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.

python -m qai_hub_models.models.resnet_mixed.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.resnet_mixed.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.
python -m qai_hub_models.models.resnet_mixed.export

How does this work?

This export script leverages Qualcomm® AI Hub 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.

import torch

import qai_hub as hub
from qai_hub_models.models.resnet_mixed 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.

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.

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. Sign up for access.

Deploying compiled model to Android

The models can be deployed using multiple runtimes:

  • TensorFlow Lite (.tflite export): This tutorial provides a guide to deploy the .tflite model in an Android application.

  • QNN (.so export ): This sample app provides instructions on how to use the .so shared library in an Android application.

View on Qualcomm® AI Hub

Get more details on ResNet-Mixed-Convolution's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of ResNet-Mixed-Convolution can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Downloads last month
93
Inference Providers NEW
Video Classification
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support