:zap: Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and the mobile terminal can run up to 178fps+
Yolo-Fastest-1.1-xl has 0.925M Params, but I don't get it how to calculate it?
If the model has been build on keras, I can use API model.summary() to get parameters.
But I don't know how to calculate automatically in darknet based framework.
I try to follow the step manually on Internet.
Conv = filter kernel-width kernel-high output channel
Depthwisth = filter kernel-width * kernel-high
Route = filter
I load Yolo-Fastest-1.1-xl.cfg weight to see each layer's information and calculate manually.
But I get my parameters about 1.88M.
Does anything wrong on my calculation? Could someone else provide the solution how to calculate the parameters of model?
As the README.md said:
Yolo-Fastest-1.1-xl has 0.925M Params, but I don't get it how to calculate it? If the model has been build on keras, I can use API model.summary() to get parameters. But I don't know how to calculate automatically in darknet based framework.
I try to follow the step manually on Internet. Conv = filter kernel-width kernel-high output channel Depthwisth = filter kernel-width * kernel-high Route = filter
I load Yolo-Fastest-1.1-xl.cfg weight to see each layer's information and calculate manually. But I get my parameters about 1.88M.
Does anything wrong on my calculation? Could someone else provide the solution how to calculate the parameters of model?