I modified the resnet50 network by： [image] [image] These are the two classes: class ChannelAttention(nn.Module): def init(self, in_planes, ratio=16): super(ChannelAttention, self).init() self.avg_pool = nn.AdaptiveAvgPool2d(1) self.max_pool = nn.AdaptiveMaxPool2d(1) self.fc1 = nn.C…

Check the implementation of ResNet50 from torchvision and implement custom network something like: class ModifiedResNet50(nn.Module): def __init__(self,): pass def forward(input): pass Then load weights from pretrained ResNet50 like given below: vanilla_resnet = models.r…

RuntimeError: Error(s) in loading state_dict for ResNet: Missing key(s) in state_dict: "ca.fc1.weight", "ca.fc2.weight", "sa.conv1.weight", "ca1.fc1.weight", "ca1.fc2.weight", "sa1.conv1.weight"

vision

sgaur (Surya Gaur) June 29, 2020, 1:56am 9

Can you please comment on this post.