NX Practice

Mix.install ([
  {:nx, "~> 0.5"},
  {:exla, "~> 0.5"},
  {:benchee, github: "bencheeorg/benchee", override: true}
])

Main

# Create Tensor
Nx.tensor([1, 2, 3])

# Create More Tensors
a = Nx.tensor([[1, 2, 3], [4, 5, 6]])
b = Nx.tensor(1.0)
c = Nx.tensor([[[[[[1.0, 2]]]]]])
dbg(a)
dbg(b)
dbg(c)

# Tensor Types Example
a = Nx.tensor([1, 2, 3])
b = Nx.tensor([1.0, 2.0, 3.0])
dbg(a)
dbg(b)

# Underflow Example
Nx.tensor(0.00000000000000000000000000000000000000000000000001)

Nx.tensor(1.0e-45, type: {:f, 64})

# Overflow Example
Nx.tensor(128, type: {:s, 8})

# Auto Type Assign Example
Nx.tensor([1.0, 2, 3])

# Example of Tensor's Shape
a = Nx.tensor([1, 2])
b = Nx.tensor([[1, 2], [3, 4]])
c = Nx.tensor([[[1, 2], [3, 4]], [[5, 6], [7, 8]]])
dbg(a)
dbg(b)
dbg(c)

# Example of a Scalar
Nx.tensor(10)

# Example of Named Tensors
Nx.tensor([[1, 2, 3], [4, 5, 6]], names: [:x, :y])

# Example of Binary Representation
a = Nx.tensor([[1, 2, 3], [4, 5, 6]])
Nx.to_binary(a)

# It's more performant to turn your data into binary representation:
<<1::64-signed-native, 2::64-signed-native, 3::64-signed-native>>
|> Nx.from_binary({:s, 64})

# Changing the Shape of a Tensor using reshape:
<<1::64-signed-native, 2::64-signed-native, 3::64-signed-native>>
|> Nx.from_binary({:s, 64})
|> Nx.reshape({1, 3})

# Shaping a Tensor
a = Nx.tensor([1, 2, 3])

a
|> Nx.as_type({:f, 32})
|> Nx.reshape({1, 3, 1})

# Bitcast Example
Nx.bitcast(a, {:f, 64})

# Element-wise Unary Operations
a = Nx.tensor([[[-1, -2, -3], [-4, -5, -6]], [[1, 2, 3], [4, 5, 6]]])
Nx.abs(a)

# Element-wise Binary Operations
a = Nx.tensor([[1, 2, 3], [4, 5, 6]])
b = Nx.tensor([[6, 7, 8], [9, 10, 11]])

Nx.add(a, b)

Nx.multiply(a, b)

Nx.add(5, Nx.tensor([1, 2, 3]))

Nx.add(Nx.tensor([1, 2, 3]), Nx.tensor([[4, 5, 6], [7, 8, 9]]))

# Reductions
revs = Nx.tensor([85, 76, 42, 34, 46, 23, 52, 99, 22, 32, 85, 51])
Nx.sum(revs)

revs = Nx.tensor(
  [
    [21, 64, 86, 26, 74, 81, 38, 79, 70, 48, 85, 33],
    [64, 82, 48, 39, 70, 71, 81, 53, 50, 67, 36, 50],
    [68, 74, 39, 78, 95, 62, 53, 21, 43, 59, 51, 88],
    [47, 74, 97, 51, 98, 47, 61, 36, 83, 55, 74, 43]
  ], names: [:year, :month])

Nx.sum(revs, axes: [:year])

Nx.sum(revs, axes: [:month])

defmodule MyModule do

  def adds_one(x) do
    Nx.add(x, 1)
  end
  
end

defmodule DefnModule do

  import Nx.Defn

  defn adds_one(x) do
    Nx.add(x, 1) |> print_expr()
  end
  
end

DefnModule.adds_one(Nx.tensor([1, 2, 3]))

# Defn Acceleration Comparison
defmodule Softmax do
  import Nx.Defn

  defn softmax(n), do: Nx.exp(n) / Nx.sum(Nx.exp(n))
end

key = Nx.Random.key(42)
{tensor, _key} = Nx.Random.uniform(key, shape: {1_000_000})

Benchee.run(
  %{
    "JIT with EXLA" => fn ->
      apply(EXLA.jit(&Softmax.softmax/1), [tensor])
      end,
    "Regular Elixir" => fn ->
      Softmax.softmax(tensor)
    end
  },
  time: 10
)