-
Notifications
You must be signed in to change notification settings - Fork 228
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
您好,我使用zynq进行仿真,那几个bin文件有些疑问请教您 #4
Comments
最近在赶deadline,时间比较紧,前面Weight_buf和Beta_buf对应的就是weight和bias,只是这边已经把每层对应的BN也合并进去了,是先合并进去得到的float32位的Weight和Bias,然后再对其进行动态定点16位的量化,后面是对应的量化参数(就是16位定点的时候小数点放哪里),分别对应输入输出、Weight和Bias,所有的代码应该会在最近全部放在github上,从如何从Darknet取参数到最终优化的都有,之前忙着做实验,目前只要写论文了,应该会每天上来写一写,可能会重新开个project,到时候会在首页贴个链接 |
Yes, actually it still need weight re-arrangement in order to increase the burst length of AXI transmission. Tonight, I will try to update the PYNQ version first. The full process will be described in another project. This project is only responsible for PYNQ. |
@Johnny-Lin @dhm2013724 @wu-y Also is inputQ, outputQ, weightQ and betaQ mean quantized input, quantized output, quantized weight and quantized beta? do you input both quantized weight, beta files and 32fp weight, beta files to the design? (I am confused because there are number of weight and beta files) what is the difference between weight and weightQ? how are they used in the design ? I am still a beginner could you briefly tell me what these mean in the code? Atleast some of them. would be a great help :) |
您好,请问您这个项目中提到的有完整过程的另一个project在哪里呢,能麻烦您附上链接吗? |
请问这里如何并入每层对应的BN参数? |
同问 |
代码中有五个bin文件:
其中 buf的有两个,Weight_buf(yolov2_w_reorg_bn_ap16_short16.bin)、Beta_buf ( yolov2_b_ap16_short16.bin ) ,这两个文件是什么文件,有什么用呢?
其中还有三个,inputQ(yolov2_bn_input_maxQ_24.bin )、weightQ(yolov2_w_reorg_bn_ap16_maxQ_23.bin)、betaQ(yolov2_b_ap16_maxQ_23.bin),这三个文件是什么文件,有什么作用呢?
yolo的权重文件只有一个,就是 .weight,如(yolov2.weights),上面的五个文件跟yolo的.weight是什么关系呢?
The text was updated successfully, but these errors were encountered: