In view of the increasing concern on model efficiency in computer vision,this paper proposed several optimization schemes to improve the flame detection models in model efficiency as well as the detection performance.A backbone network (FIRE-Net) was constructed from a multi-convolution combined structure,which can efficiently extract rich flame features from multiple scales.Then an improved weighted bidirectional feature pyramid network (BiFPN-mini) was used to quickly achieve multi-scale feature fusion.In addition,a new attention mechanism (FIRE-Attention) was proposed to make the detector more sensitive to flame characteristics.The above optimizations were combined to develop a new flame detector abbreviated as FIRE-DET,which was then trained on self-built dataset and tested on internet videos.The experimental results showed that the FIRE-DET outperformed mainstream algorithms by its flame recognition accuracy of 97％ and frame rate of 85 FPS,thus provides a more common solution to solve the flame detection.