Question About the adjust_scales2image function in functions.py

[myunghakLee]

Thank you for your wonderful code. It really helped me a lot.

What I want to ask is about a function.py I want to know why used scale2stop = math.ceil(math.log(min([opt.max_size, max([real_.shape[2], real_.shape[3]])]) / max([real_.shape[2], real_.shape[3]]),opt.scale_factor_init)) twice in the code below.

def adjust_scales2image(real_,opt):
    #opt.num_scales = int((math.log(math.pow(opt.min_size / (real_.shape[2]), 1), opt.scale_factor_init))) + 1
    opt.num_scales = math.ceil((math.log(math.pow(opt.min_size / (min(real_.shape[2], real_.shape[3])), 1), opt.scale_factor_init))) + 1
    scale2stop = math.ceil(math.log(min([opt.max_size, max([real_.shape[2], real_.shape[3]])]) / max([real_.shape[2], real_.shape[3]]),opt.scale_factor_init))
    opt.stop_scale = opt.num_scales - scale2stop
    opt.scale1 = min(opt.max_size / max([real_.shape[2], real_.shape[3]]),1)  # min(250/max([real_.shape[0],real_.shape[1]]),1)
    real = imresize(real_, opt.scale1, opt)
    #opt.scale_factor = math.pow(opt.min_size / (real.shape[2]), 1 / (opt.stop_scale))
    opt.scale_factor = math.pow(opt.min_size/(min(real.shape[2],real.shape[3])),1/(opt.stop_scale))
    scale2stop = math.ceil(math.log(min([opt.max_size, max([real_.shape[2], real_.shape[3]])]) / max([real_.shape[2], real_.shape[3]]),opt.scale_factor_init))
    opt.stop_scale = opt.num_scales - scale2stop
    return real

I've checked the code works properly when I deleted the second one.
I think the second one should be replaced with scale2stop = math.ceil(math.log(min([opt.max_size, max([real_.shape[2], real_.shape[3]])]) / max([real_.shape[2], real_.shape[3]]),opt.scale_factor))

Thank you for your time to read

[tamarott]

Please see #49 and #76