Darknet Neural Network

Darknet apply a single neural network to the full image. This network divides the image into regions and predicts bounding boxes and probabilities for each region. These bounding boxes are weighted by the predicted probabilities. Darknet has several advantages over classifier-based systems. It looks at the whole image at test time so its predictions are informed by global context in the image. It also makes predictions with a single network evaluation unlike systems like R-CNN which require thousands for a single image. This makes it extremely fast, more than 1000x faster than R-CNN and 100x faster than Fast R-CNN.

Darknet将单个神经网络直接应用于整张输入图像。该网络会将图像划分为多个区域，并为每个区域预测边界框（bounding box）与对应置信度概率。所得边界框将依据预测得到的概率进行加权处理。相较于基于分类器的目标检测系统，Darknet具备多项显著优势：在测试阶段，Darknet可对整张图像进行全局感知，因此其预测结果能够利用图像中的全局上下文信息；且仅需一次神经网络前向传播即可完成所有预测，而诸如R-CNN这类系统，仅单张图像就需要执行数千次计算。这使得Darknet的检测速度极快，其运算速度较R-CNN提升超1000倍，较Fast R-CNN提升超100倍。