ResNet-18 is one of the shallowest models in the Residual Network (ResNet) family, consisting of 18 layers. ResNet was proposed by Kaiming He and his team at Microsoft Research in 2015 to address the vanishing and exploding gradient problems in deep neural networks. ResNet-18 introduces residual connections (skip connections), which allow the input to bypass several layers, making the network easier to train and enabling greater depth. Despite its relatively low number of parameters, ResNet-18 achieves high classification accuracy and is widely used in tasks like image classification and object detection.

Source model

• Input shape: 224x224
• Number of parameters: 11.15M
• Model size: 44.58M
• Output shape: 1x1000

Source model repository: ResNet-18

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 APLUX 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