Squeezenet model ONNX export

Hi,
I have some questions regarding the squeeznet model.

I failed at exporting the model to ONNX with the following error "ONNX export failed : Couldn't export operator aten:max_pool2d_with_indices".
I noticed that in /torch/onnx/symbolic.py , the use of "ceil_mode" is not supported in max_pool2d_with_indices.
After setting "ceil_mode" to False for all occurrences of "MaxPool2d", the export succeeds.

I also noticed that, when using the exported model mentioned above, the Pytorch results do not match the ONNX results, the reason being the use of "nn.Dropout(0.5)".

My questions are :

 1- Is there a particular reason "ceil_mode" is being used? and would there be a concern with setting it to False for the export to be possible? I could submit a PR with this change if no concern is noted.

 2- Why is "Dropout" used in the model outside of training? Could we remove it? 

Thanks

Start by reproducing the Squeezenet ONNX export failure and inspect /torch/onnx/symbolic.py, especially max_pool2d_with_indices and ceil_mode handling. Compare the exported model's results with PyTorch while accounting for the model's nn.Dropout(0.5). Done means the intended ceil_mode and Dropout behavior is decided and the export and output mismatch are addressed or clearly documented.