ResNet is fully convolutional and the implementation should allow inputs to be any size.
Be able to train out of the box on CIFAR-10, 100, and ImageNet. (Implementation incomplete)
Pretrained Model
To convert the published Caffe pretrained model, run convert.py. However
Caffe is annoying to install so I'm providing a download of the output of
convert.py:
This code depends on TensorFlow git commit
cf7ce8or later because ResNet needs 1x1 convolutions with stride 2. TF 0.8 is not new
enough.
The convert.py script checks that activations are similiar to the caffe version
but it's not exactly the same. This is probably due to differences between how
TF and Caffe handle padding. Also preprocessing is done with color-channel means
instead of pixel-wise means.