fkm3

Hi. Our current Gradient module actually supports reverse mode differentiation, but does not support forward mode. Did you run into any problems using it?

Hi. Did you give the `--extra-include-dirs= and --extra-lib-dirs=` part a try? I've forgotten where cabal looks for libraries. In our CI, we are putting them in `/usr/local/lib` and `/usr/local/include`: https://github.com/tensorflow/haskell/blob/master/ci_build/Dockerfile#L40....

I've haven't tried it, but if you managed to install tensorflow for windows already, then you probably have most of the dependencies. I think the main extra dependency we have...

Thanks @EvgenyVorobyov! > Try stack install tensorflow. If build fails on c2hs, check generated types. My problem was that c2hs generates CULLong for size_t when tensorflows's sources require CULong. That...

Sure, added a link in https://github.com/tensorflow/haskell/pull/171. If you have a cool example or something, we can add that as a code snippet as well.

Sorry for the slow reply. I'm adding that example in https://github.com/tensorflow/haskell/pull/174, thanks! Also, feel free to send PRs for this sort of thing if you like (licensing issues aren't usually...

I need to improve that error message. It just means that the gradients aren't implemented for BiasAdd. There need to be implementations for both `numOutputs` and `opGrad`.

If you want biasAdd because of conv2d with NCHW format, then, coincidentally, I'm doing something similar, and I think you can work around the lack of biasAdd by using normal...

(warning: haven't tried to compile any of this) Loosely speaking, you can use the `>>=` operator to work with values inside the monad ```haskell let xDim = 40 yDim =...

There isn't any support for the tensorflow debugger right now. I'm not sure what work is required to support it. A short-term workaround might be to use `asGraphDef` to get...