|
import torch |
|
from itertools import product as product |
|
import numpy as np |
|
from math import ceil |
|
|
|
|
|
class PriorBox(object): |
|
def __init__(self, cfg, image_size=None, phase='train'): |
|
super(PriorBox, self).__init__() |
|
self.msizes = cfg['msizes'] |
|
self.steps = cfg['steps'] |
|
self.clip = cfg['clip'] |
|
self.image_size = image_size |
|
self.feature_maps = [[ceil(self.image_size[0]/step), ceil(self.image_size[1]/step)] for step in self.steps] |
|
self.name = "s" |
|
|
|
def forward(self): |
|
anchors = [] |
|
for k, f in enumerate(self.feature_maps): |
|
msizes = self.msizes[k] |
|
for i, j in product(range(f[0]), range(f[1])): |
|
for msize in msizes: |
|
s_kx = msize / self.image_size[1] |
|
s_ky = msize / self.image_size[0] |
|
dense_cx = [x * self.steps[k] / self.image_size[1] for x in [j + 0.5]] |
|
dense_cy = [y * self.steps[k] / self.image_size[0] for y in [i + 0.5]] |
|
for cy, cx in product(dense_cy, dense_cx): |
|
anchors += [cx, cy, s_kx, s_ky] |
|
|
|
|
|
output = torch.Tensor(anchors).view(-1, 4) |
|
if self.clip: |
|
output.clamp_(max=1, min=0) |
|
return output |
|
|
