Pytorch：训练网络的常用辅助代码

1. 查看定义好的Model和参数情况

''' 如何查看定义好的model和参数情况 '''
model = CNN3_FC()
print(model)

'''     查看参数的名字和shape '''
for name,params in model.named_parameters():
    print(type(params)) # <class 'torch.nn.parameter.Parameter'>
    # print(f'{name}:{params.numel()}')
    print(f'{name}:{params.size()}')


'''     简易版:查看总体参数和需要训练的参数 '''
total_num = sum(param.numel() for param in model.parameters())
trainable_num = sum(param.numel() for param in model.parameters() if param.requires_grad)