deepali-c
deepali-c
Thanks @aymericdamien, the error on `evaluate()` is gone now and the score is being returned. Could you please also suggest how I can use the result array returned by `predict()`...
@soumith, @ShahriarSS, the above solution resolves this issue. Do you think this can be added as fix to the example?
I observed the following error while executing the inception v3 sample: `RuntimeError: Calculated padded input size per channel: (3 x 3). Kernel size: (5 x 5). Kernel size can't be...
I have tried below mentioned two approaches, for using new backend with `1 gpu` : 1. Modified` train.py` to setup device context as in `Theano-MPI`: (Along with changes to use...
@hma02 , Thank you so much for these changes. The `1 gpu` example works with `libgpuarray` on my setup as well. I am working on the `2 gpu` sample next.
Thanks @hma02 . I observed the following error while executing the `2 gpu sample` with `gpuarray` backend: ``` Process Process-2: Process Process-1: Traceback (most recent call last): Traceback (most recent...
Thanks @hma02. I got it now.