DarkNet is a convolutional neural network architecture that serves as the backbone for the YOLO (You Only Look Once) object detection series. It is designed for efficient feature extraction with a focus on real-time object detection applications.
DarkNetTiny is the compact version designed for embedded deployment. It features Leaky ReLU activations, batch normalization after every convolutional layer, and uses global average pooling instead of fully connected layers to reduce parameter count.
The straightforward stack of convolutional layers makes it easy to implement and modify, while maintaining competitive performance on edge devices.
Dataset details:
link
Number of classes: 1000.
To perform the quantization, we calibrated the activations with a random subset of the training set.
For the sake of simplicity, the accuracy reported here was estimated on the 50000 labelled images of the validation set.
Please refer to the stm32ai-modelzoo-services GitHub
here[1] -
Dataset: Imagenet (ILSVRC 2012) —
https://www.image-net.org/
