-
Hi!
I would like to obtain the derivative of the flow at fixed time. However, it errors with
```
ERROR: MethodError: no method matching exponential!(::Base.ReshapedArray{ForwardDiff.Dual{Forwa…
-
One great aspect of a differentiable analysis workflow is that it allows to use gradient-based methods to optimize the analysis. This might mean for example optimizing a jet pT cut to minimize the unc…
-
-
## 🚀 Feature
It would be extremely useful to add gradient support for the [box3d_overlap](https://github.com/facebookresearch/pytorch3d/blob/d049cd2e0102a6b2e08bf2b595131d5177638081/pytorch3d/ops…
-
Vectorize over `knots` and `intervals` instead of enforcing `knots` and `intervals` , but we need to make `knots` and `intervals` part of `params` possibly (in the compute function definition)
See …
-
I want to use the `stack` function introduced in Julia 1.9 in my model but Flux.jl (or its backend) cannot auto-differentiate it.
```julia
using Flux
nn = Dense(3 => 2)
x = randn(Float32, 3, 5…
-
### 🚀 The feature, motivation and pitch
In the documentation, dtype is often used as a type hint where in actuality only differentiable dtypes are allowed (float and complex). Therefore the request t…
-
```julia
julia> function f(x, bias)
jac = Zygote.jacobian(x->x.^3, x)[1]
return jac * x .+ bias
end
f (generic function with 1 method)
julia> x,bias =…
-
- https://arxiv.org/abs/2006.12057
- 2020
概要-
ディープニューラルネットワーク(DNN)は、物体の検出や画像のセグメンテーションなど、視覚に関連するタスクにおいて顕著な性能向上を示している。
その成功にもかかわらず、一般的には、シーンの3D情報を収集したり、簡単にアノテーションを付けたりすることができないため、画像を形成する3Dオブジェ…
e4exp updated
2 years ago
-
say f(x)=2x, f'(10) gets 2. Seen from @code_llvm, the gradient function of `f` simply returns 2.
What is differentiable type in Zygote? What is non-differentiable type? Here 10 is integer type. Do…