densenet issue

[lovecodng]

I am working on the Stochastic Variational Deep Kernel Learning example on the following link:
https://docs.gpytorch.ai/en/latest/examples/06_PyTorch_NN_Integration_DKL/Deep_Kernel_Learning_DenseNet_CIFAR_Tutorial.html
when I run the code I get the following error:

ModuleNotFoundError                       Traceback (most recent call last)
Cell In[70], line 1
----> 1 from densenet import DenseNet
      3 class DenseNetFeatureExtractor(DenseNet):
      4     def forward(self, x):

ModuleNotFoundError: No module named 'densenet'

I tried to overcome this error by adding the following two lines:

import torchvision.models.densenet
from torchvision.models.densenet import DenseNet

And indeed the error disappeared however, I am getting new error as listed below, Any advice?

(Epoch 1) Minibatch: 0%
0/2 [00:00<?, ?it/s]
---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
Cell In[58], line 3
      1 for epoch in range(1, n_epochs + 1):
      2     with gpytorch.settings.use_toeplitz(False):
----> 3         train(epoch)
      4         test()
      5     scheduler.step()

Cell In[57], line 23, in train(epoch)
     21     data, target = data.cuda(), target.cuda()
     22 optimizer.zero_grad()
---> 23 output = model(data)
     24 loss = -mll(output, target)
     25 loss.backward()

File ~\anaconda3\envs\python3-env\lib\site-packages\gpytorch\module.py:30, in Module.__call__(self, *inputs, **kwargs)
     29 def __call__(self, *inputs, **kwargs):
---> 30     outputs = self.forward(*inputs, **kwargs)
     31     if isinstance(outputs, list):
     32         return [_validate_module_outputs(output) for output in outputs]

Cell In[56], line 13, in DKLModel.forward(self, x)
     12 def forward(self, x):
---> 13     features = self.feature_extractor(x)
     14     features = self.scale_to_bounds(features)
     15     # This next line makes it so that we learn a GP for each feature

File ~\anaconda3\envs\python3-env\lib\site-packages\torch\nn\modules\module.py:1194, in Module._call_impl(self, *input, **kwargs)
   1190 # If we don't have any hooks, we want to skip the rest of the logic in
   1191 # this function, and just call forward.
   1192 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
   1193         or _global_forward_hooks or _global_forward_pre_hooks):
-> 1194     return forward_call(*input, **kwargs)
   1195 # Do not call functions when jit is used
   1196 full_backward_hooks, non_full_backward_hooks = [], []

Cell In[54], line 7, in DenseNetFeatureExtractor.forward(self, x)
      5 features = self.features(x)
      6 out = F.relu(features, inplace=True)
----> 7 out = F.avg_pool2d(out, kernel_size=self.avgpool_size).view(features.size(0), -1)
      8 return out

File ~\anaconda3\envs\python3-env\lib\site-packages\torch\nn\modules\module.py:1269, in Module.__getattr__(self, name)
   1267     if name in modules:
   1268         return modules[name]
-> 1269 raise AttributeError("'{}' object has no attribute '{}'".format(
   1270     type(self).__name__, name))

AttributeError: 'DenseNetFeatureExtractor' object has no attribute 'avgpool_size'

[Balandat]

I guess this is b/c this is based on an old DenseNet implementation. Not sure how to solve this specifically but I guess looking at the current code should be a start: https://github.com/pytorch/vision/blob/main/torchvision/models/densenet.py#L213-L215 (using adaptive_avg_pool2d and dropping the classifier) is what I'd try...