摘要: # def conv_bn(inp, oup, stride):# return nn.Sequential(# nn.Conv2d(inp, oup, 3, stride, 1, bias=False),# nn.BatchNorm2d(oup),# nn.ReLU(inplace=True)# 阅读全文
posted @ 2020-05-25 22:16 haiyanli 阅读(242) 评论(0) 推荐(0) 编辑
摘要: 尝试修改网络结构的记录: 1、resnet18修改为vgg16,epoch=2时效果差点,修改: model_conv = models.vgg16(pretrained=True) #model_conv = models.restnet18(pretrained=True) 2、如果每个stag 阅读全文
posted @ 2020-05-25 05:01 haiyanli 阅读(123) 评论(0) 推荐(0) 编辑