kailaix
kailaix
Convolution in 1D. The implementation follows https://github.com/tensorflow/tensorflow/blob/r1.12/tensorflow/python/ops/nn_ops.py
One of the PR from https://github.com/malmaud/TensorFlow.jl/pull/478 1. Update the tensorflow version from 1.10.0 to 1.12.0 (newest) 2. Fix `transpose` base index (0=>1)
This is one of the PRs in https://github.com/malmaud/TensorFlow.jl/pull/478
When there is a Variable in the upstream operations, Julia custom operator will fail. Example: `JuliaOpModule` in ADCME.jl ```julia push!(LOAD_PATH, "..") include("../JuliaOpModule.jl") using ADCME import JuliaOpModule:do_it, DoIt! x = Variable(rand(100))...
BFGS is very useful for the engineering optimization problem. It seems not trivial to have an elegant solution for implementing or wrapping a GPU-accelerated BFGS optimizer.
When `EBC[10,1] = -1`, `FBC[10,1] = -1`, `FBC[10,1]=-1` is ignored Add an exception in the codes.