摘要:
特征金字塔,用上采样+3x3卷积得到P3~P5 P6和P7通过C5得到 import torch.nn as nn class FPN(nn.Module): def __init__(self, C3_size, C4_size, C5_size, feature_size=256): # fea 阅读全文
摘要:
懒,就直接用Resnet50了 先写个残差块 class Bottleneck(nn.Module): expansion = 4 def __init__(self, inplanes, planes, stride=1, downsample=None): super(Bottleneck, s 阅读全文