-
图 1 YOLOv2网络结构
Figure 1. YOLOv2 network structure
-
图 2 加速器数据流框架
Figure 2. Accelerator data flow framework
-
图 3 粗粒度优化示意图
Figure 3. Schematic diagram of coarse-grained optimization
-
图 4 优化前后FPGA中的乘加操作对比
Figure 4. Comparison of multiplication and addition operations in FPGA before and after optimization
-
图 5 32位浮点数和16位定点数表示对比
Figure 5. Comparison between 32-bit floating-point numbers and 16-bit fixed-point numbers
-
图 6 卷积模块展开示意图
Figure 6. Schematic diagram of convolution module expansion
-
图 7 池化模块示意图
Figure 7. Schematic diagram of pooling module
-
图 8 重排序示意图
Figure 8. Schematic diagram of reordering
-
图 9 系统硬件加速器架构
Figure 9. System hardware accelerator architecture
-
图 10 YOLOv2网络硬件加速系统
Figure 10. YOLOv2 network hardware acceleration system
-
图 11 实验环境与检测结果
Figure 11. Experimental environment and test results
-
Consume resources (Data precision) DSP LUT Adders(Float-32) 2 214 Multiplier(Float-32) 3 135 Adders(Fixed-16) - 47 Multiplier(Fixed-16) 1 101 表 1 不同数据精度消耗资源对比
Table 1. Comparison of resource consumption with different data accuracy
-
Resoures Used Available Utilization/% LUTs 35 977 53 200 67.62 FF 32 049 106 400 30.12 BRAM_18K 178 280 63.57 DSP48E 152 220 69.09 表 2 加速器资源消耗
Table 2. Accelerator resource consumption
-
表 3 与其他FPGA加速器设计的比较
Table 3. Comparison with other FPGA accelerator designs
图共
11 个 表共
3 个