1、Motivation：

I wanna modify the value of some param;

I wanna check the value of some param.

The needed function:

2、state_dict() #generator type

model.modules()#generator type

named_parameters()#OrderDict type

from torch import nnimport torch#creat a simple modelmodel = nn.Sequential( nn.Conv3d(1,16,kernel_size=1), nn.Conv3d(16,2,kernel_size=1))#tend to print the W of this layerinput = torch.randn([1,1,16,256,256])if torch.cuda.is_available(): print('cuda is avaliable') model.cuda() input = input.cuda()#打印某一层的参数名for name in model.state_dict(): print(name)#Then I konw that the name of target layer is '1.weight'#schemem1(recommended)print(model.state_dict()['1.weight'])#scheme2params = list(model.named_parameters())#get the index by debugingprint(params[2][0])#nameprint(params[2][1].data)#data#scheme3params = {}#change the tpye of 'generator' into dictfor name,param in model.named_parameters():params[name] = param.detach().cpu().numpy()print(params['0.weight'])#scheme4for layer in model.modules():if(isinstance(layer,nn.Conv3d)): print(layer.weight)#打印每一层的参数名和参数值#schemem1(recommended)for name,param in model.named_parameters(): print(name，param)#scheme2for name in model.state_dict(): print(name) print(model.state_dict()[name])

以上这篇pytorch获取模型某一层参数名及参数值方式就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持。