dhm2013724/xilinx_fpga_hls-mapping-neural-network-to-hardware

At present, just an example to show how to map the detection algorithm YOLOv2 from model to FPGA

示例：如何将目标检测算法YOLOv2映射到Xilinx FPGA Zedboard

由于目前处于Deadline时期，要等下个礼拜才有时间把完整的整个流程在Github上分享一下，现在只能先用中文简单描述一下整个流程：从Darknet 框架中的YOLOv2模型到最终生成bitstream的过程。
（1）需要先从Darknet官网下载darknet框架，然后将其中YOLOv2的权重提取出来。由于YOLOv2的卷积层基本都会跟着BatchNormalization，所以在提取权重的过程中，就将YOLOv2中的weight和bias分别和对应的BN乘在一起具体公式可以参考文献[1]，公式如下：
y=(x-bn0)/sqrt(bn1) (1)
z=sc0y+sc1 (2)
所以，可以将(1)与(2)合并，得到：
y=Ax+B (3)
其中 A= sc0/sqpr(bn1), B=sc1-sc0*bn0/sqrt(bn1)
这部分代码放在framework目录下

参考文献：
[1] An Automatic RTL Compiler for High-Throughput FPGA Implementation of Diverse Deep Convolutional Neural Networks

xilinx_fpga_hls-mapping-neural-network-to-hardware's Issues

是不是我darknet版本的问题，layer l中无法找到成员numload,你能告诉我如何解决这个问题吗

是不是我darknet版本的问题，layer l中无法找到成员numload,你能告诉我如何解决这个问题吗

some errors happened when I used the weights.bin and bias.bin in jupter notebook

hello~
when I applied the files(weights.bin and bias.bin) to the jupyter notebook, it appeared an error:
could not broadcast input array from shape (50941792) into shape (25470896). Then I changed the shape (25470896) into shape (50941792), but it appeared another error:Failed to allocate Memory!
Can you help me?
The codes I changed are as follows:

weight_base_buffer = xlnk.cma_array(shape=(25470896,), dtype=np.uint32)

weight_base_buffer = xlnk.cma_array(shape=(50941792,), dtype=np.uint32)
print("100M",weight_base_buffer.physical_address)
WEIGHT_BASE = weight_base_buffer.physical_address

bate_base_buffer = xlnk.cma_array(shape=(5381,), dtype=np.uint32)
print("32k",bate_base_buffer.physical_address)
BETA_BASE=bate_base_buffer.physical_address

img_base_buffer = xlnk.cma_array(shape=(4194304,), dtype=np.int32)
print("16M",img_base_buffer.physical_address)
IMG_MEM = img_base_buffer.physical_address
params_wight = np.fromfile("weights.bin", dtype=np.uint32)
np.copyto(weight_base_buffer, params_wight)
print("yolov2_weight copy ok\n")

params_bais = np.fromfile("bias.bin", dtype=np.uint32)
np.copyto(bate_base_buffer, params_bais)
print("yolov2_bais copy ok\n")