Bendtorch.MSE: def of bendtorch@1.3.0.0
Import: import bendtorch@1.3.0.0/main.bend as Bendtorch
Lines 3269-3274 of bendtorch@1.3.0.0/main.bend: https://jend.leeeet.dev/read.txt?path=bendtorch@1.3.0.0/main.bend&start_line=3269&end_line=3274

import Base
import bend-ml-tensor-array@0.1.18.0/main.bend as TA

# mean squared error over every number (PyTorch's F.mse_loss); its gradient is 2 (y - t) / (n*c); the squares summed
# as a tree
def MSE(+n: Nat, +c: Nat, y: TA.Mat<n, c>, t: TA.Mat<n, c>) -> LossOut<TA.Mat<n, c>>:
  match y t:
    case TA.Mat{ya} TA.Mat{ta}:
      mse_fin(n, c, U32.from_nat(Nat.mul(n, c)), F32.from_nat(Nat.mul(n, c)), mse_l(Nat.sub(Nat.mul(n, c), 1n), 0, (2.0 / F32.from_nat(Nat.mul(n, c)) : F32), zeros_a(Nat.mul(n, c)), Array.get(F32, ya, 0), Array.get(F32, ta, 0)))

Uses (13):
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=Array.get
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=F32
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=F32.div
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=F32.from_nat
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=Nat
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=Nat.mul
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=Nat.sub
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=U32.from_nat
  https://jend.leeeet.dev/definition.txt?path=bend-ml-tensor-array@0.1.19.0/main.bend&name=Mat
  https://jend.leeeet.dev/definition.txt?path=bendtorch@1.3.0.0/main.bend&name=LossOut
  https://jend.leeeet.dev/definition.txt?path=bendtorch@1.3.0.0/main.bend&name=mse_fin
  https://jend.leeeet.dev/definition.txt?path=bendtorch@1.3.0.0/main.bend&name=mse_l
  https://jend.leeeet.dev/definition.txt?path=bendtorch@1.3.0.0/main.bend&name=zeros_a