ResNet-34
Image Classification
INT8
FP16
post
ResNet-34: Image Classification

ResNet-34 is a deep convolutional neural network in the ResNet (Residual Network) family, introduced by Kaiming He and colleagues in 2015. ResNet-34 consists of 34 layers and effectively addresses the vanishing gradient problem in deep networks by introducing residual (skip) connections, making the network easier to train as depth increases. These residual connections allow input features to bypass several layers, reducing training difficulty and enhancing performance. With greater depth than ResNet-18, ResNet-34 maintains a relatively low parameter count, making it suitable for tasks balancing computational efficiency and accuracy. This model is widely used in computer vision tasks like image classification, object detection, and semantic segmentation.

Source model

  • Input shape: 224x224
  • Number of parameters: 20.79M
  • Model size: 83.14M
  • Output shape: 1x1000

Source model repository: resnet

Performance Reference
Device
Backend
Precision
Inference Time
Accuracy Loss
File Size
Model Optimization

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.

Model Inference

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
License
Source Model:BSD-3-CLAUSE
Deployable Model:APLUX-MODEL-FARM-LICENSE
Performance Reference
Device
Backend
Precision
Inference Time
Accuracy Loss
File Size