ABSTRACT :
Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency. First, we propose a weighted bi-directional feature pyramid network (BIFPN), which allows easy and fast multi-scale feature fusion; Second, we propose a compound scaling method that uniformly scales the resolution, depth, and width for all backbone, feature network, and box/class prediction networks at the same time. Based on these optimizations and Efficient Net backbones, we have developed a new family of object detectors, called Efficient Det, which consistently achieve much better efficiency than prior art across a wide spectrum of resource constraints. In particular, with single-model and single-scale, our EfficientDetD7 achieves state-of-the-art 52.2 AP on COCO test-dev with 52M parameters and 325B FLOPs1 , being 4x – 9x smaller and using 13x – 42x fewer FLOPs than previous detector.
EXITING SYSTEM :
One-Stage Detectors: Existing object detectors are mostly categorized by whether they have a region-of interest proposal step (two-stage [9, 32, 3, 11]) or not (one stage [33, 24, 30, 21]). While two-stage detectors tend to be more flexible and more accurate, one-stage detectors are often considered to be simpler and more efficient by leveraging predefined anchors [14]. Recently, one-stage detectors have attracted substantial attention due to their efficiency and simplicity [18, 39, 41]. In this paper, we mainly follow the one-stage detector design, and we show it is possible to achieve both better efficiency and higher accuracy with optimized network architectures.
DISADVANTAGES OF EXISTING SYSTEM :
1) Less accuracy
2)low Efficiency
PROPOSED SYSTEM :
In this section, we first formulate the multi-scale feature fusion problem, and then introduce the main ideas for our proposed BIFPN: efficient bidirectional cross-scale connections and weighted feature fusion
Multi-scale feature fusion aims to aggregate features at different resolutions. Formally, given a list of multi-scale features P~ in = (P in l1 , Pin l2 ,…), where P in li represents the feature at level li , our goal is to find a transformation f that can effectively aggregate different features and output a list of new features: P~ out = f(P~ in). As a concrete example, Figure 2(a) shows the conventional top-down FPN [20]. It takes level 3-7 input features P~ in = (P in 3 ,…Pin 7 ), where P in i represents a feature level with resolution of 1/2 i of the input images. For instance, if input resolution is 640×640, then P in 3 represents feature level 3 (640/2 3 = 80) with resolution 80×80, while P in 7 represents feature level 7 with resolution 5×5. The conventional FPN aggregates multi-scale features in a top-down manner:
ADVANTAGES OF PROPOSED SYSTEM :
1) High accuracy
2)High efficiency
SYSTEM REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10
HARDWARE REQUIREMENTS:
Processor : Core I3
RAM Capacity : 2 GB
Hard Disk : 250 GB
Monitor : 15″ Color
Mouse : 2 or 3 Button Mouse
Key Board : Windows 08/10
