pytorch 实现在预训练模型的 input上增减通道
时间：2021-06-03 09:11:57|栏目：Python代码|点击： 次
如何把imagenet预训练的模型，输入层的通道数随心所欲的修改，从而来适应自己的任务
#增加一个通道 w = layers[0].weight layers[0] = nn.Conv2d(4, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False) layers[0].weight = torch.nn.Parameter(torch.cat((w, w[:, :1, :, :]), dim=1)) #方式2 w = layers[0].weight layers[0] = nn.Conv2d(4, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False) layers[0].weight = torch.nn.Parameter(torch.cat((w, torch.zeros(64, 1, 7, 7)), dim=1)) #单通道输入 layers[0] = nn.Conv2d(1, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False) layers[0].weight = torch.nn.Parameter(w[:, :1, :, :])
