import torchoutil as to

probs = to.as_tensor([[0.9, 0.1], [0.4, 0.6]])
names = to.probs_to_name(probs, idx_to_name={0: "Cat", 1: "Dog"})
# ["Cat", "Dog"]

import torchoutil as to

multihot = to.as_tensor([[1, 0, 0], [0, 1, 1], [0, 0, 0]])
indices = to.multihot_to_indices(multihot)
# [[0], [1, 2], []]

import torchoutil as to

x1 = to.as_tensor([1, 2])
print(isinstance(x1, to.Tensor2D))  # False
x2 = to.as_tensor([[1, 2], [3, 4]])
print(isinstance(x2, to.Tensor2D))  # True

import torchoutil as to

x1 = to.as_tensor([1, 2], dtype=to.int)
print(isinstance(x1, to.SignedIntegerTensor))  # True

x2 = to.as_tensor([1, 2], dtype=to.long)
print(isinstance(x2, to.SignedIntegerTensor))  # True

x3 = to.as_tensor([1, 2], dtype=to.float)
print(isinstance(x3, to.SignedIntegerTensor))  # False

import torchoutil as to

x1 = to.rand(10, 3, 1)
x2 = to.pad_dim(x, target_length=5, dim=1, pad_value=-1)
# x2 has shape (10, 5, 1)

import torchoutil as to

tensors = [to.rand(10, 2), to.rand(5, 3), to.rand(0, 5)]
padded = to.pad_and_stack_rec(tensors, pad_value=0)
# padded has shape (10, 5)

import torchoutil as to

x = to.as_tensor([3, 1, 2])
mask = to.lengths_to_non_pad_mask(x, max_len=4)
# Each row i contains x[i] True values for non-padding mask
# tensor([[True, True, True, False],
#         [True, False, False, False],
#         [True, True, False, False]])

import torchoutil as to

x = to.as_tensor([1, 2, 3, 4])
mask = to.as_tensor([True, True, False, False])
result = to.masked_mean(x, mask)
# result contains the mean of the values marked as True: 1.5

import torchoutil as to

x = to.as_tensor([1, 2, 3, 4])
result = to.insert_at_indices(x, indices=[0, 2], values=5)
# result contains tensor with inserted values: tensor([5, 1, 2, 5, 3, 4])

import torchoutil as to

perm = to.randperm(10)
inv_perm = to.get_inverse_perm(perm)

x1 = to.rand(10)
x2 = x1[perm]
x3 = x2[inv_perm]
# inv_perm are indices that allow us to get x3 from x2, i.e. x1 == x3 here

from torchaudio.datasets import SPEECHCOMMANDS
from torchaudio.transforms import Spectrogram
from torchoutil import nn
from torchoutil.extras.hdf import pack_to_hdf

speech_commands_root = "path/to/speech_commands"
packed_root = "path/to/packed_dataset.hdf"

dataset = SPEECHCOMMANDS(speech_commands_root, download=True, subset="validation")
# dataset[0] is a tuple, contains waveform and other metadata

class MyTransform(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        self.spectrogram_extractor = Spectrogram()

    def forward(self, item):
        waveform = item[0]
        spectrogram = self.spectrogram_extractor(waveform)
        return (spectrogram,) + item[1:]

pack_to_hdf(dataset, packed_root, MyTransform())

from torchoutil.extras.hdf import HDFDataset

packed_root = "path/to/packed_dataset.hdf"
packed_dataset = HDFDataset(packed_root)
packed_dataset[0]  # == first transformed item, i.e. transform(dataset[0])