GitLab

tensors with different sizes and it will zero pad them as needed.

since that's a little different in cuDNN.  I also removed my CUDA code for
doing batch normalization and replaced it with cuDNN's new batch normalization
methods.

Finally, I forgot to add a convolutional option to the bn_ object.  Now it has
one so you can set the mode however you like, either BATCH_NORM_FC or
BATCH_NORM_CONV.

cudnnAddTensor() function and updated the specs and asserts accordingly.

batch_normalize_conv.

of add to them so that it's consistent with how the layer interface expects
this to be done.

for this object.

runs on the GPU, and made affine_transform() take only tensors.

use either CPU or GPU.  Fixed a bug in gemm().

form.

code based on how dlib was built.  All the layer implementations will interact
with these functions.