DenseNet (Densely Connected Convolutional Networks) is a convolutional neural network architecture that introduces dense connections, where the output of each layer is directly connected to every subsequent layer. This design helps mitigate the vanishing gradient problem, promotes feature reuse, and reduces the number of parameters, thereby improving training efficiency. DenseNet is highly parameter-efficient and computationally efficient, making it suitable for tasks like image classification and object detection. It performs particularly well in scenarios with limited data. Key variants of DenseNet include DenseNet-121, DenseNet-169, and DenseNet-201.
Source model
- Input shape: 224x224
- Number of paramaters: 7.61M
- Model size: 30.81M
- Output shape: 1x1000
Source model repository: densenet
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