How to load TRAINED model

[ElinorG11]

Hello,

Thank you very much for this repo. I'm looking for trained model parameters, do you happen to have it for resnet20 and resnet32?

Thank you.

[qilong-zhang]

I have the same question.
I load the checkpoint by the following code:

model = resnet.__dict__['resnet32']()
check_point = torch.load('resnet32-d509ac18.th')
model.load_state_dict(check_point['state_dict'])

However, it cannot load and report

Missing key(s) in state_dict: "conv1.weight", "bn1.weight", "bn1.bias", "bn1.running_mean", "bn1.running_var", "layer1.0.conv1.weight", "layer1.0.bn1.weight", "layer1.0.bn1.bias", "layer1.0.bn1.running_mean", "layer1.0.bn1.running_var", "layer1.0.conv2.weight", "layer1.0.bn2.weight", "layer1.0.bn2.bias", "layer1.0.bn2.running_mean", "layer1.0.bn2.running_var", "layer1.1.conv1.weight", "layer1.1.bn1.weight", "layer1.1.bn1.bias", "layer1.1.bn1.running_mean", "layer1.1.bn1.running_var", "layer1.1.conv2.weight", "layer1.1.bn2.weight", "layer1.1.bn2.bias", "layer1.1.bn2.running_mean", "layer1.1.bn2.running_var", "layer1.2.conv1.weight", "layer1.2.bn1.weight", "layer1.2.bn1.bias", "layer1.2.bn1.running_mean", "layer1.2.bn1.running_var", "layer1.2.conv2.weight", "layer1.2.bn2.weight", "layer1.2.bn2.bias", "layer1.2.bn2.running_mean", "layer1.2.bn2.running_var", "layer1.3.conv1.weight", "layer1.3.bn1.weight", "layer1.3.bn1.bias", "layer1.3.bn1.running_mean", "layer1.3.bn1.running_var", "layer1.3.conv2.weight", "layer1.3.bn2.weight", "layer1.3.bn2.bias", "layer1.3.bn2.running_mean", "layer1.3.bn2.running_var", "layer1.4.conv1.weight", "layer1.4.bn1.weight", "layer1.4.bn1.bias", "layer1.4.bn1.running_mean", "layer1.4.bn1.running_var", "layer1.4.conv2.weight", "layer1.4.bn2.weight", "layer1.4.bn2.bias", "layer1.4.bn2.running_mean", "layer1.4.bn2.running_var", "layer2.0.conv1.weight", "layer2.0.bn1.weight", "layer2.0.bn1.bias", "layer2.0.bn1.running_mean", "layer2.0.bn1.running_var", "layer2.0.conv2.weight", "layer2.0.bn2.weight", "layer2.0.bn2.bias", "layer2.0.bn2.running_mean", "layer2.0.bn2.running_var", "layer2.1.conv1.weight", "layer2.1.bn1.weight", "layer2.1.bn1.bias", "layer2.1.bn1.running_mean", "layer2.1.bn1.running_var", "layer2.1.conv2.weight", "layer2.1.bn2.weight", "layer2.1.bn2.bias", "layer2.1.bn2.running_mean", "layer2.1.bn2.running_var", "layer2.2.conv1.weight", "layer2.2.bn1.weight", "layer2.2.bn1.bias", "layer2.2.bn1.running_mean", "layer2.2.bn1.running_var", "layer2.2.conv2.weight", "layer2.2.bn2.weight", "layer2.2.bn2.bias", "layer2.2.bn2.running_mean", "layer2.2.bn2.running_var", "layer2.3.conv1.weight", "layer2.3.bn1.weight", "layer2.3.bn1.bias", "layer2.3.bn1.running_mean", "layer2.3.bn1.running_var", "layer2.3.conv2.weight", "layer2.3.bn2.weight", "layer2.3.bn2.bias", "layer2.3.bn2.running_mean", "layer2.3.bn2.running_var", "layer2.4.conv1.weight", "layer2.4.bn1.weight", "layer2.4.bn1.bias", "layer2.4.bn1.running_mean", "layer2.4.bn1.running_var", "layer2.4.conv2.weight", "layer2.4.bn2.weight", "layer2.4.bn2.bias", "layer2.4.bn2.running_mean", "layer2.4.bn2.running_var", "layer3.0.conv1.weight", "layer3.0.bn1.weight", "layer3.0.bn1.bias", "layer3.0.bn1.running_mean", "layer3.0.bn1.running_var", "layer3.0.conv2.weight", "layer3.0.bn2.weight", "layer3.0.bn2.bias", "layer3.0.bn2.running_mean", "layer3.0.bn2.running_var", "layer3.1.conv1.weight", "layer3.1.bn1.weight", "layer3.1.bn1.bias", "layer3.1.bn1.running_mean", "layer3.1.bn1.running_var", "layer3.1.conv2.weight", "layer3.1.bn2.weight", "layer3.1.bn2.bias", "layer3.1.bn2.running_mean", "layer3.1.bn2.running_var", "layer3.2.conv1.weight", "layer3.2.bn1.weight", "layer3.2.bn1.bias", "layer3.2.bn1.running_mean", "layer3.2.bn1.running_var", "layer3.2.conv2.weight", "layer3.2.bn2.weight", "layer3.2.bn2.bias", "layer3.2.bn2.running_mean", "layer3.2.bn2.running_var", "layer3.3.conv1.weight", "layer3.3.bn1.weight", "layer3.3.bn1.bias", "layer3.3.bn1.running_mean", "layer3.3.bn1.running_var", "layer3.3.conv2.weight", "layer3.3.bn2.weight", "layer3.3.bn2.bias", "layer3.3.bn2.running_mean", "layer3.3.bn2.running_var", "layer3.4.conv1.weight", "layer3.4.bn1.weight", "layer3.4.bn1.bias", "layer3.4.bn1.running_mean", "layer3.4.bn1.running_var", "layer3.4.conv2.weight", "layer3.4.bn2.weight", "layer3.4.bn2.bias", "layer3.4.bn2.running_mean", "layer3.4.bn2.running_var", "linear.weight", "linear.bias". 
        Unexpected key(s) in state_dict: "module.conv1.weight", "module.bn1.weight", "module.bn1.bias", "module.bn1.running_mean", "module.bn1.running_var", "module.layer1.0.conv1.weight", "module.layer1.0.bn1.weight", "module.layer1.0.bn1.bias", "module.layer1.0.bn1.running_mean", "module.layer1.0.bn1.running_var", "module.layer1.0.conv2.weight", "module.layer1.0.bn2.weight", "module.layer1.0.bn2.bias", "module.layer1.0.bn2.running_mean", "module.layer1.0.bn2.running_var", "module.layer1.1.conv1.weight", "module.layer1.1.bn1.weight", "module.layer1.1.bn1.bias", "module.layer1.1.bn1.running_mean", "module.layer1.1.bn1.running_var", "module.layer1.1.conv2.weight", "module.layer1.1.bn2.weight", "module.layer1.1.bn2.bias", "module.layer1.1.bn2.running_mean", "module.layer1.1.bn2.running_var", "module.layer1.2.conv1.weight", "module.layer1.2.bn1.weight", "module.layer1.2.bn1.bias", "module.layer1.2.bn1.running_mean", "module.layer1.2.bn1.running_var", "module.layer1.2.conv2.weight", "module.layer1.2.bn2.weight", "module.layer1.2.bn2.bias", "module.layer1.2.bn2.running_mean", "module.layer1.2.bn2.running_var", "module.layer1.3.conv1.weight", "module.layer1.3.bn1.weight", "module.layer1.3.bn1.bias", "module.layer1.3.bn1.running_mean", "module.layer1.3.bn1.running_var", "module.layer1.3.conv2.weight", "module.layer1.3.bn2.weight", "module.layer1.3.bn2.bias", "module.layer1.3.bn2.running_mean", "module.layer1.3.bn2.running_var", "module.layer1.4.conv1.weight", "module.layer1.4.bn1.weight", "module.layer1.4.bn1.bias", "module.layer1.4.bn1.running_mean", "module.layer1.4.bn1.running_var", "module.layer1.4.conv2.weight", "module.layer1.4.bn2.weight", "module.layer1.4.bn2.bias", "module.layer1.4.bn2.running_mean", "module.layer1.4.bn2.running_var", "module.layer2.0.conv1.weight", "module.layer2.0.bn1.weight", "module.layer2.0.bn1.bias", "module.layer2.0.bn1.running_mean", "module.layer2.0.bn1.running_var", "module.layer2.0.conv2.weight", "module.layer2.0.bn2.weight", "module.layer2.0.bn2.bias", "module.layer2.0.bn2.running_mean", "module.layer2.0.bn2.running_var", "module.layer2.1.conv1.weight", "module.layer2.1.bn1.weight", "module.layer2.1.bn1.bias", "module.layer2.1.bn1.running_mean", "module.layer2.1.bn1.running_var", "module.layer2.1.conv2.weight", "module.layer2.1.bn2.weight", "module.layer2.1.bn2.bias", "module.layer2.1.bn2.running_mean", "module.layer2.1.bn2.running_var", "module.layer2.2.conv1.weight", "module.layer2.2.bn1.weight", "module.layer2.2.bn1.bias", "module.layer2.2.bn1.running_mean", "module.layer2.2.bn1.running_var", "module.layer2.2.conv2.weight", "module.layer2.2.bn2.weight", "module.layer2.2.bn2.bias", "module.layer2.2.bn2.running_mean", "module.layer2.2.bn2.running_var", "module.layer2.3.conv1.weight", "module.layer2.3.bn1.weight", "module.layer2.3.bn1.bias", "module.layer2.3.bn1.running_mean", "module.layer2.3.bn1.running_var", "module.layer2.3.conv2.weight", "module.layer2.3.bn2.weight", "module.layer2.3.bn2.bias", "module.layer2.3.bn2.running_mean", "module.layer2.3.bn2.running_var", "module.layer2.4.conv1.weight", "module.layer2.4.bn1.weight", "module.layer2.4.bn1.bias", "module.layer2.4.bn1.running_mean", "module.layer2.4.bn1.running_var", "module.layer2.4.conv2.weight", "module.layer2.4.bn2.weight", "module.layer2.4.bn2.bias", "module.layer2.4.bn2.running_mean", "module.layer2.4.bn2.running_var", "module.layer3.0.conv1.weight", "module.layer3.0.bn1.weight", "module.layer3.0.bn1.bias", "module.layer3.0.bn1.running_mean", "module.layer3.0.bn1.running_var", "module.layer3.0.conv2.weight", "module.layer3.0.bn2.weight", "module.layer3.0.bn2.bias", "module.layer3.0.bn2.running_mean", "module.layer3.0.bn2.running_var", "module.layer3.1.conv1.weight", "module.layer3.1.bn1.weight", "module.layer3.1.bn1.bias", "module.layer3.1.bn1.running_mean", "module.layer3.1.bn1.running_var", "module.layer3.1.conv2.weight", "module.layer3.1.bn2.weight", "module.layer3.1.bn2.bias", "module.layer3.1.bn2.running_mean", "module.layer3.1.bn2.running_var", "module.layer3.2.conv1.weight", "module.layer3.2.bn1.weight", "module.layer3.2.bn1.bias", "module.layer3.2.bn1.running_mean", "module.layer3.2.bn1.running_var", "module.layer3.2.conv2.weight", "module.layer3.2.bn2.weight", "module.layer3.2.bn2.bias", "module.layer3.2.bn2.running_mean", "module.layer3.2.bn2.running_var", "module.layer3.3.conv1.weight", "module.layer3.3.bn1.weight", "module.layer3.3.bn1.bias", "module.layer3.3.bn1.running_mean", "module.layer3.3.bn1.running_var", "module.layer3.3.conv2.weight", "module.layer3.3.bn2.weight", "module.layer3.3.bn2.bias", "module.layer3.3.bn2.running_mean", "module.layer3.3.bn2.running_var", "module.layer3.4.conv1.weight", "module.layer3.4.bn1.weight", "module.layer3.4.bn1.bias", "module.layer3.4.bn1.running_mean", "module.layer3.4.bn1.running_var", "module.layer3.4.conv2.weight", "module.layer3.4.bn2.weight", "module.layer3.4.bn2.bias", "module.layer3.4.bn2.running_mean", "module.layer3.4.bn2.running_var", "module.linear.weight", "module.linear.bias". 

@akamaster Could you give us some advice?

[jimmyl02]

Might be because it is parallelized, this thread offers good insight: https://discuss.pytorch.org/t/loading-weights-from-dataparallel-models/20570

I would try wrapping the model in DataParallel then trying to load it or I believe there are some ways to change attributes such that it works without the dataparall wrapper.

[YihaoChan]

Hi, I solved this problem. Hope this helps you.

import torch
from resnet import *
import dill  # in order to save Lambda Layer

# your devices
device_ids = [0, 1]

# the network architecture coresponding to the checkpoint
model = resnet20()

# remember to set map_location
check_point = torch.load('resnet20-12fca82f.th', map_location='cuda:%d' % device_ids[0])

# cause the model are saved from Parallel, we need to wrap it
model = torch.nn.DataParallel(model, device_ids=device_ids)
model.load_state_dict(check_point['state_dict'])

# pay attention to .module! without this, if you load the model, it will be attached with [Parallel.module]
# that will lead to some trouble!
torch.save(model.module, 'resnet20_check_point.pth', pickle_module=dill)

# load the converted pretrained model
net = torch.load('resnet20_check_point.pth', map_location='cuda:%d' % device_ids[0])
x = torch.rand(size=(1, 3, 32, 32)).cuda(device_ids[0])
out = net(x)
print(out)

[YihaoChan]

I have the same question. I load the checkpoint by the following code:

model = resnet.__dict__['resnet32']()
check_point = torch.load('resnet32-d509ac18.th')
model.load_state_dict(check_point['state_dict'])

However, it cannot load and report

Missing key(s) in state_dict: "conv1.weight", "bn1.weight", "bn1.bias", "bn1.running_mean", "bn1.running_var", "layer1.0.conv1.weight", "layer1.0.bn1.weight", "layer1.0.bn1.bias", "layer1.0.bn1.running_mean", "layer1.0.bn1.running_var", "layer1.0.conv2.weight", "layer1.0.bn2.weight", "layer1.0.bn2.bias", "layer1.0.bn2.running_mean", "layer1.0.bn2.running_var", "layer1.1.conv1.weight", "layer1.1.bn1.weight", "layer1.1.bn1.bias", "layer1.1.bn1.running_mean", "layer1.1.bn1.running_var", "layer1.1.conv2.weight", "layer1.1.bn2.weight", "layer1.1.bn2.bias", "layer1.1.bn2.running_mean", "layer1.1.bn2.running_var", "layer1.2.conv1.weight", "layer1.2.bn1.weight", "layer1.2.bn1.bias", "layer1.2.bn1.running_mean", "layer1.2.bn1.running_var", "layer1.2.conv2.weight", "layer1.2.bn2.weight", "layer1.2.bn2.bias", "layer1.2.bn2.running_mean", "layer1.2.bn2.running_var", "layer1.3.conv1.weight", "layer1.3.bn1.weight", "layer1.3.bn1.bias", "layer1.3.bn1.running_mean", "layer1.3.bn1.running_var", "layer1.3.conv2.weight", "layer1.3.bn2.weight", "layer1.3.bn2.bias", "layer1.3.bn2.running_mean", "layer1.3.bn2.running_var", "layer1.4.conv1.weight", "layer1.4.bn1.weight", "layer1.4.bn1.bias", "layer1.4.bn1.running_mean", "layer1.4.bn1.running_var", "layer1.4.conv2.weight", "layer1.4.bn2.weight", "layer1.4.bn2.bias", "layer1.4.bn2.running_mean", "layer1.4.bn2.running_var", "layer2.0.conv1.weight", "layer2.0.bn1.weight", "layer2.0.bn1.bias", "layer2.0.bn1.running_mean", "layer2.0.bn1.running_var", "layer2.0.conv2.weight", "layer2.0.bn2.weight", "layer2.0.bn2.bias", "layer2.0.bn2.running_mean", "layer2.0.bn2.running_var", "layer2.1.conv1.weight", "layer2.1.bn1.weight", "layer2.1.bn1.bias", "layer2.1.bn1.running_mean", "layer2.1.bn1.running_var", "layer2.1.conv2.weight", "layer2.1.bn2.weight", "layer2.1.bn2.bias", "layer2.1.bn2.running_mean", "layer2.1.bn2.running_var", "layer2.2.conv1.weight", "layer2.2.bn1.weight", "layer2.2.bn1.bias", "layer2.2.bn1.running_mean", "layer2.2.bn1.running_var", "layer2.2.conv2.weight", "layer2.2.bn2.weight", "layer2.2.bn2.bias", "layer2.2.bn2.running_mean", "layer2.2.bn2.running_var", "layer2.3.conv1.weight", "layer2.3.bn1.weight", "layer2.3.bn1.bias", "layer2.3.bn1.running_mean", "layer2.3.bn1.running_var", "layer2.3.conv2.weight", "layer2.3.bn2.weight", "layer2.3.bn2.bias", "layer2.3.bn2.running_mean", "layer2.3.bn2.running_var", "layer2.4.conv1.weight", "layer2.4.bn1.weight", "layer2.4.bn1.bias", "layer2.4.bn1.running_mean", "layer2.4.bn1.running_var", "layer2.4.conv2.weight", "layer2.4.bn2.weight", "layer2.4.bn2.bias", "layer2.4.bn2.running_mean", "layer2.4.bn2.running_var", "layer3.0.conv1.weight", "layer3.0.bn1.weight", "layer3.0.bn1.bias", "layer3.0.bn1.running_mean", "layer3.0.bn1.running_var", "layer3.0.conv2.weight", "layer3.0.bn2.weight", "layer3.0.bn2.bias", "layer3.0.bn2.running_mean", "layer3.0.bn2.running_var", "layer3.1.conv1.weight", "layer3.1.bn1.weight", "layer3.1.bn1.bias", "layer3.1.bn1.running_mean", "layer3.1.bn1.running_var", "layer3.1.conv2.weight", "layer3.1.bn2.weight", "layer3.1.bn2.bias", "layer3.1.bn2.running_mean", "layer3.1.bn2.running_var", "layer3.2.conv1.weight", "layer3.2.bn1.weight", "layer3.2.bn1.bias", "layer3.2.bn1.running_mean", "layer3.2.bn1.running_var", "layer3.2.conv2.weight", "layer3.2.bn2.weight", "layer3.2.bn2.bias", "layer3.2.bn2.running_mean", "layer3.2.bn2.running_var", "layer3.3.conv1.weight", "layer3.3.bn1.weight", "layer3.3.bn1.bias", "layer3.3.bn1.running_mean", "layer3.3.bn1.running_var", "layer3.3.conv2.weight", "layer3.3.bn2.weight", "layer3.3.bn2.bias", "layer3.3.bn2.running_mean", "layer3.3.bn2.running_var", "layer3.4.conv1.weight", "layer3.4.bn1.weight", "layer3.4.bn1.bias", "layer3.4.bn1.running_mean", "layer3.4.bn1.running_var", "layer3.4.conv2.weight", "layer3.4.bn2.weight", "layer3.4.bn2.bias", "layer3.4.bn2.running_mean", "layer3.4.bn2.running_var", "linear.weight", "linear.bias". 
        Unexpected key(s) in state_dict: "module.conv1.weight", "module.bn1.weight", "module.bn1.bias", "module.bn1.running_mean", "module.bn1.running_var", "module.layer1.0.conv1.weight", "module.layer1.0.bn1.weight", "module.layer1.0.bn1.bias", "module.layer1.0.bn1.running_mean", "module.layer1.0.bn1.running_var", "module.layer1.0.conv2.weight", "module.layer1.0.bn2.weight", "module.layer1.0.bn2.bias", "module.layer1.0.bn2.running_mean", "module.layer1.0.bn2.running_var", "module.layer1.1.conv1.weight", "module.layer1.1.bn1.weight", "module.layer1.1.bn1.bias", "module.layer1.1.bn1.running_mean", "module.layer1.1.bn1.running_var", "module.layer1.1.conv2.weight", "module.layer1.1.bn2.weight", "module.layer1.1.bn2.bias", "module.layer1.1.bn2.running_mean", "module.layer1.1.bn2.running_var", "module.layer1.2.conv1.weight", "module.layer1.2.bn1.weight", "module.layer1.2.bn1.bias", "module.layer1.2.bn1.running_mean", "module.layer1.2.bn1.running_var", "module.layer1.2.conv2.weight", "module.layer1.2.bn2.weight", "module.layer1.2.bn2.bias", "module.layer1.2.bn2.running_mean", "module.layer1.2.bn2.running_var", "module.layer1.3.conv1.weight", "module.layer1.3.bn1.weight", "module.layer1.3.bn1.bias", "module.layer1.3.bn1.running_mean", "module.layer1.3.bn1.running_var", "module.layer1.3.conv2.weight", "module.layer1.3.bn2.weight", "module.layer1.3.bn2.bias", "module.layer1.3.bn2.running_mean", "module.layer1.3.bn2.running_var", "module.layer1.4.conv1.weight", "module.layer1.4.bn1.weight", "module.layer1.4.bn1.bias", "module.layer1.4.bn1.running_mean", "module.layer1.4.bn1.running_var", "module.layer1.4.conv2.weight", "module.layer1.4.bn2.weight", "module.layer1.4.bn2.bias", "module.layer1.4.bn2.running_mean", "module.layer1.4.bn2.running_var", "module.layer2.0.conv1.weight", "module.layer2.0.bn1.weight", "module.layer2.0.bn1.bias", "module.layer2.0.bn1.running_mean", "module.layer2.0.bn1.running_var", "module.layer2.0.conv2.weight", "module.layer2.0.bn2.weight", "module.layer2.0.bn2.bias", "module.layer2.0.bn2.running_mean", "module.layer2.0.bn2.running_var", "module.layer2.1.conv1.weight", "module.layer2.1.bn1.weight", "module.layer2.1.bn1.bias", "module.layer2.1.bn1.running_mean", "module.layer2.1.bn1.running_var", "module.layer2.1.conv2.weight", "module.layer2.1.bn2.weight", "module.layer2.1.bn2.bias", "module.layer2.1.bn2.running_mean", "module.layer2.1.bn2.running_var", "module.layer2.2.conv1.weight", "module.layer2.2.bn1.weight", "module.layer2.2.bn1.bias", "module.layer2.2.bn1.running_mean", "module.layer2.2.bn1.running_var", "module.layer2.2.conv2.weight", "module.layer2.2.bn2.weight", "module.layer2.2.bn2.bias", "module.layer2.2.bn2.running_mean", "module.layer2.2.bn2.running_var", "module.layer2.3.conv1.weight", "module.layer2.3.bn1.weight", "module.layer2.3.bn1.bias", "module.layer2.3.bn1.running_mean", "module.layer2.3.bn1.running_var", "module.layer2.3.conv2.weight", "module.layer2.3.bn2.weight", "module.layer2.3.bn2.bias", "module.layer2.3.bn2.running_mean", "module.layer2.3.bn2.running_var", "module.layer2.4.conv1.weight", "module.layer2.4.bn1.weight", "module.layer2.4.bn1.bias", "module.layer2.4.bn1.running_mean", "module.layer2.4.bn1.running_var", "module.layer2.4.conv2.weight", "module.layer2.4.bn2.weight", "module.layer2.4.bn2.bias", "module.layer2.4.bn2.running_mean", "module.layer2.4.bn2.running_var", "module.layer3.0.conv1.weight", "module.layer3.0.bn1.weight", "module.layer3.0.bn1.bias", "module.layer3.0.bn1.running_mean", "module.layer3.0.bn1.running_var", "module.layer3.0.conv2.weight", "module.layer3.0.bn2.weight", "module.layer3.0.bn2.bias", "module.layer3.0.bn2.running_mean", "module.layer3.0.bn2.running_var", "module.layer3.1.conv1.weight", "module.layer3.1.bn1.weight", "module.layer3.1.bn1.bias", "module.layer3.1.bn1.running_mean", "module.layer3.1.bn1.running_var", "module.layer3.1.conv2.weight", "module.layer3.1.bn2.weight", "module.layer3.1.bn2.bias", "module.layer3.1.bn2.running_mean", "module.layer3.1.bn2.running_var", "module.layer3.2.conv1.weight", "module.layer3.2.bn1.weight", "module.layer3.2.bn1.bias", "module.layer3.2.bn1.running_mean", "module.layer3.2.bn1.running_var", "module.layer3.2.conv2.weight", "module.layer3.2.bn2.weight", "module.layer3.2.bn2.bias", "module.layer3.2.bn2.running_mean", "module.layer3.2.bn2.running_var", "module.layer3.3.conv1.weight", "module.layer3.3.bn1.weight", "module.layer3.3.bn1.bias", "module.layer3.3.bn1.running_mean", "module.layer3.3.bn1.running_var", "module.layer3.3.conv2.weight", "module.layer3.3.bn2.weight", "module.layer3.3.bn2.bias", "module.layer3.3.bn2.running_mean", "module.layer3.3.bn2.running_var", "module.layer3.4.conv1.weight", "module.layer3.4.bn1.weight", "module.layer3.4.bn1.bias", "module.layer3.4.bn1.running_mean", "module.layer3.4.bn1.running_var", "module.layer3.4.conv2.weight", "module.layer3.4.bn2.weight", "module.layer3.4.bn2.bias", "module.layer3.4.bn2.running_mean", "module.layer3.4.bn2.running_var", "module.linear.weight", "module.linear.bias". 

@akamaster Could you give us some advice?

Please have a look to my solution above. Hope it can help you.