Mul¶
Description¶
This module performs the elementwise multiplication of tensors.
Initializing¶
def __init__(self, name=None):
Parameters
Parameter | Allowed types | Description | Default |
---|---|---|---|
name | str | Layer name | None |
Explanations
-
Examples¶
Necessary imports.
import numpy as np
from PuzzleLib.Backend import gpuarray
from PuzzleLib.Modules import Mul
Info
gpuarray
is required to properly place the tensor in the GPU
maps, h, w = 1, 2, 2
data1 = gpuarray.to_gpu(np.arange(maps * h * w).reshape((maps, h, w)).astype(np.float32))
data2 = gpuarray.to_gpu(np.arange(maps * h * w).reshape((maps, h, w)).astype(np.float32))
print(data1)
[[[0. 1.]
[2. 3.]]]
mul = Mul()
print(mul([data1, data2]))
[[[0. 1.]
[4. 9.]]]