ResNet-101 is a deep convolutional neural network in the ResNet (Residual Network) series, introduced by Kaiming He and his team in 2015. ResNet-101 consists of 101 layers and utilizes residual connections (skip connections) to address the vanishing gradient problem in deep networks, allowing it to train very deep structures without loss of accuracy. These residual connections let input features be directly passed to subsequent layers, simplifying training and enhancing model performance. ResNet-101 performs excellently in tasks such as image classification, object detection, and semantic segmentation, with its depth making it suitable for complex tasks requiring high-level feature representation. Despite its larger parameter count, its high accuracy and strong transferability have led to its widespread use in computer vision applications.

Source model

• Input shape: 224x224
• Number of parameters: 42.49M
• Model size: 169.79M
• Output shape: 1x1000

Source model repository: ResNet-101

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