Cannot manually assign new parameters via layer name

Question

I'm trying to manually assign new weights to my pytorch model. I can assign new weights like this:

import scipy.io as sio
import torch

caffe_params = sio.loadmat('export_conv1_1.mat')
net.conv1_1.weight = torch.nn.Parameter(torch.from_numpy(caffe_params['w']))
net.conv1_1.bias = torch.nn.Parameter(torch.from_numpy(caffe_params['b']))

caffe_params = sio.loadmat('export_conv2_1.mat')
net.conv2_1.weight = torch.nn.Parameter(torch.from_numpy(caffe_params['w']))
net.conv2_1.bias = torch.nn.Parameter(torch.from_numpy(caffe_params['b']))

Since I have a lot of layers I don't want to manually assign every layer via it's name. Instead I want rather to loop over a list of layer names and assign them automatically. Something like this:

varList = ['conv2_1','conv2_2']

for name in varList:
    caffe_params = sio.loadmat(rootDir + 'export_' + name + '.mat')
    setattr(net, name + '.weight' ,torch.nn.Parameter(torch.from_numpy(caffe_params['w'])))
    setattr(net, name + '.bias' ,torch.nn.Parameter(torch.from_numpy(caffe_params['b'])))

Unfortunately this doesn't work. I guess setattr doesn't work with either pytorch weigths or with attributes of type layername.weight, which means the attribute to assign has depth 2 with respect to net.

score 0 · Answer 1 · answered Mar 05 '18 at 23:12

Does the following work?

for name in varList:
    caffe_params = sio.loadmat(rootDir + 'export_' + name + '.mat')
    getattr(net, name).weight.data.copy_(torch.from_numpy(caffe_params['w']))
    getattr(net, name).bias.data.copy_(torch.from_numpy(caffe_params['b']))

Cannot manually assign new parameters via layer name

1 Answers1