2201_75347732的博客

原创 lol英雄联盟角色识别

image_tensor = transform(image).unsqueeze(0).to(device) # 进行预处理和转换，并添加批次维度。image_tensor = transform(image).unsqueeze(0).to(device) # 进行预处理和转换，并添加批次维度。self.conv1 = nn.Conv2d(3, 16, 3, 1) # 输入3通道，输出16通道。transforms.Normalize((0.5,), (0.5,)) # 归一化到[-1, 1]