Inception-v3 is the third version of the Inception series proposed by Google, known for its efficiency in convolutional neural networks and widely used for image classification tasks. The key idea behind Inception-v3 is its modular design, where multiple convolution filters of different sizes run in parallel, enabling the extraction of multi-scale features to improve the network’s representational power. The model incorporates techniques like batch normalization, factorized convolutions, and auxiliary classifiers, which reduce computational complexity while enhancing stability and accuracy. Inception-v3 has demonstrated outstanding performance on the ImageNet classification task, making it a key benchmark in deep learning.

Source model

• Input shape: 299x299
• Number of paramaters: 25.9M
• Model size: 90.9M
• Output shape: 1x1000

Source model repository: Inception-v3

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