ResNeXt-101 is a high-performance deep convolutional neural network that enhances model capacity by introducing the concept of "cardinality" (number of parallel branches), building upon the classic ResNet architecture. It employs grouped convolutions to create multi-branch structures, where each branch independently transforms features, boosting diversity without significantly increasing parameters. By integrating residual learning, it retains ResNet’s optimization stability and gradient propagation efficiency, while achieving finer feature extraction through increased branch counts (e.g., 32 groups). ResNeXt-101 demonstrates exceptional classification accuracy on datasets like ImageNet and, with its modular design, easily adapts to object detection (e.g., Mask R-CNN) and semantic segmentation tasks. Balancing computational efficiency and performance, it is ideal for compute-intensive scenarios demanding high precision.

Source model

• Input shape: 224x224
• Number of parameters: 84.68MB
• Model size: 338.37MB
• Output shape: 1x1000

The source model can be found here

When the user has fine-tuned the source model, the model conversion process must be performed again.

Users can refer to either of the following two methods to complete the model conversion:

• Using AIMO for model conversion: Click Model Conversion Reference in the Performance Reference section on the right to view the conversion steps.

• Using Qualcomm QNN for model conversion: Please refer to the Qualcomm QNN Documentation.

The model performance benchmarks and example code provided by Model Farm are all implemented based on the AIDLux AidLite SDK.

For models in .bin format, you can use either of the following two inference engines to run inference on Qualcomm chips:

Inference using APLUX AidLite: please refer to the APLUX AidLite Developer Documentation

Inference using Qualcomm QNN: Please refer to the Qualcomm QNN Documentation

Inference Example Code

The inference example code is implemented using the AidLite SDK.

Click Model & Code to download the model files and the inference code package. The file structure is as follows:

/model_farm_{model_name}_aidlite
    
    |__ models # folder where model files are stored

    |__ python # aidlite python model inference example

    |__ cpp # aidlite cpp model inference example

    |__ README.md