31 KiB
31 KiB
import torch
x = torch.tensor([[1,2,3,4], [5,6,7,8]])
print(x * 10)tensor([[10, 20, 30, 40],
[50, 60, 70, 80]])
x = torch.tensor([[1,2,3,4], [5,6,7,8]])
y = x.add(10)
print(y)tensor([[11, 12, 13, 14],
[15, 16, 17, 18]])
y = torch.tensor([2, 3, 1, 0]) # y.shape == (4)
y = y.view(4,1) # y.shape == (4, 1)x = torch.randn(10,1,10)
z1 = torch.squeeze(x, 1) # similar to np.squeeze()
# The same operation can be directly performed on
# x by calling squeeze and the dimension to squeeze out
z2 = x.squeeze(1)
assert torch.all(z1 == z2) # all the elements in both tensors are equal
print('Squeeze:\n', x.shape, z1.shape)Squeeze: torch.Size([10, 1, 10]) torch.Size([10, 10])
x = torch.randn(10,10)
print(x.shape)
# torch.size(10,10)
z1 = x.unsqueeze(0)
print(z1.shape)
# torch.size(1,10,10)
# The same can be achieved using [None] indexing
# Adding None will auto create a fake dim at the
# specified axis
x = torch.randn(10,10)
z2, z3, z4 = x[None], x[:,None], x[:,:,None]
print(z2.shape, z3.shape, z4.shape)torch.Size([10, 10]) torch.Size([1, 10, 10]) torch.Size([1, 10, 10]) torch.Size([10, 1, 10]) torch.Size([10, 10, 1])
x = torch.tensor([[1,2,3,4], [5,6,7,8]])
print(torch.matmul(x, y))tensor([[11],
[35]])
print(x@y)tensor([[11],
[35]])
import torch
x = torch.randn(10,10,10)
z = torch.cat([x,x], axis=0) # np.concatenate()
print('Cat axis 0:', x.shape, z.shape)
# Cat axis 0: torch.Size([10, 10, 10]) torch.Size([20, 10, 10])
z = torch.cat([x,x], axis=1) # np.concatenate()
print('Cat axis 1:', x.shape, z.shape)
# Cat axis 1: torch.Size([10, 10, 10]) torch.Size([10, 20, 10])Cat axis 0: torch.Size([10, 10, 10]) torch.Size([20, 10, 10]) Cat axis 1: torch.Size([10, 10, 10]) torch.Size([10, 20, 10])
x = torch.arange(25).reshape(5,5)
print('Max:', x.shape, x.max()) Max: torch.Size([5, 5]) tensor(24)
x.max(dim=0)torch.return_types.max( values=tensor([20, 21, 22, 23, 24]), indices=tensor([4, 4, 4, 4, 4]))
m, argm = x.max(dim=1)
print('Max in axis 1:\n', m, argm) Max in axis 1: tensor([ 4, 9, 14, 19, 24]) tensor([4, 4, 4, 4, 4])
x = torch.randn(10,20,30)
z = x.permute(2,0,1) # np.permute()
print('Permute dimensions:', x.shape, z.shape)Permute dimensions: torch.Size([10, 20, 30]) torch.Size([30, 10, 20])
dir(torch.Tensor)['T', '__abs__', '__add__', '__and__', '__array__', '__array_priority__', '__array_wrap__', '__bool__', '__class__', '__contains__', '__cuda_array_interface__', '__deepcopy__', '__delattr__', '__delitem__', '__dict__', '__dir__', '__div__', '__doc__', '__eq__', '__float__', '__floordiv__', '__format__', '__ge__', '__getattribute__', '__getitem__', '__gt__', '__hash__', '__iadd__', '__iand__', '__idiv__', '__ifloordiv__', '__ilshift__', '__imul__', '__index__', '__init__', '__init_subclass__', '__int__', '__invert__', '__ior__', '__ipow__', '__irshift__', '__isub__', '__iter__', '__itruediv__', '__ixor__', '__le__', '__len__', '__long__', '__lshift__', '__lt__', '__matmul__', '__mod__', '__module__', '__mul__', '__ne__', '__neg__', '__new__', '__nonzero__', '__or__', '__pow__', '__radd__', '__rdiv__', '__reduce__', '__reduce_ex__', '__repr__', '__reversed__', '__rfloordiv__', '__rmul__', '__rpow__', '__rshift__', '__rsub__', '__rtruediv__', '__setattr__', '__setitem__', '__setstate__', '__sizeof__', '__str__', '__sub__', '__subclasshook__', '__truediv__', '__weakref__', '__xor__', '_backward_hooks', '_base', '_cdata', '_coalesced_', '_dimI', '_dimV', '_grad', '_grad_fn', '_indices', '_is_view', '_make_subclass', '_nnz', '_update_names', '_values', '_version', 'abs', 'abs_', 'absolute', 'absolute_', 'acos', 'acos_', 'acosh', 'acosh_', 'add', 'add_', 'addbmm', 'addbmm_', 'addcdiv', 'addcdiv_', 'addcmul', 'addcmul_', 'addmm', 'addmm_', 'addmv', 'addmv_', 'addr', 'addr_', 'align_as', 'align_to', 'all', 'allclose', 'angle', 'any', 'apply_', 'argmax', 'argmin', 'argsort', 'as_strided', 'as_strided_', 'as_subclass', 'asin', 'asin_', 'asinh', 'asinh_', 'atan', 'atan2', 'atan2_', 'atan_', 'atanh', 'atanh_', 'backward', 'baddbmm', 'baddbmm_', 'bernoulli', 'bernoulli_', 'bfloat16', 'bincount', 'bitwise_and', 'bitwise_and_', 'bitwise_not', 'bitwise_not_', 'bitwise_or', 'bitwise_or_', 'bitwise_xor', 'bitwise_xor_', 'bmm', 'bool', 'byte', 'cauchy_', 'ceil', 'ceil_', 'char', 'cholesky', 'cholesky_inverse', 'cholesky_solve', 'chunk', 'clamp', 'clamp_', 'clamp_max', 'clamp_max_', 'clamp_min', 'clamp_min_', 'clone', 'coalesce', 'conj', 'contiguous', 'copy_', 'cos', 'cos_', 'cosh', 'cosh_', 'cpu', 'cross', 'cuda', 'cummax', 'cummin', 'cumprod', 'cumsum', 'data', 'data_ptr', 'deg2rad', 'deg2rad_', 'dense_dim', 'dequantize', 'det', 'detach', 'detach_', 'device', 'diag', 'diag_embed', 'diagflat', 'diagonal', 'digamma', 'digamma_', 'dim', 'dist', 'div', 'div_', 'dot', 'double', 'dtype', 'eig', 'element_size', 'eq', 'eq_', 'equal', 'erf', 'erf_', 'erfc', 'erfc_', 'erfinv', 'erfinv_', 'exp', 'exp_', 'expand', 'expand_as', 'expm1', 'expm1_', 'exponential_', 'fft', 'fill_', 'fill_diagonal_', 'flatten', 'flip', 'fliplr', 'flipud', 'float', 'floor', 'floor_', 'floor_divide', 'floor_divide_', 'fmod', 'fmod_', 'frac', 'frac_', 'gather', 'ge', 'ge_', 'geometric_', 'geqrf', 'ger', 'get_device', 'grad', 'grad_fn', 'gt', 'gt_', 'half', 'hardshrink', 'has_names', 'histc', 'ifft', 'imag', 'index_add', 'index_add_', 'index_copy', 'index_copy_', 'index_fill', 'index_fill_', 'index_put', 'index_put_', 'index_select', 'indices', 'int', 'int_repr', 'inverse', 'irfft', 'is_coalesced', 'is_complex', 'is_contiguous', 'is_cuda', 'is_distributed', 'is_floating_point', 'is_leaf', 'is_meta', 'is_mkldnn', 'is_nonzero', 'is_pinned', 'is_quantized', 'is_same_size', 'is_set_to', 'is_shared', 'is_signed', 'is_sparse', 'isclose', 'isfinite', 'isinf', 'isnan', 'istft', 'item', 'kthvalue', 'layout', 'le', 'le_', 'lerp', 'lerp_', 'lgamma', 'lgamma_', 'log', 'log10', 'log10_', 'log1p', 'log1p_', 'log2', 'log2_', 'log_', 'log_normal_', 'log_softmax', 'logaddexp', 'logaddexp2', 'logcumsumexp', 'logdet', 'logical_and', 'logical_and_', 'logical_not', 'logical_not_', 'logical_or', 'logical_or_', 'logical_xor', 'logical_xor_', 'logsumexp', 'long', 'lstsq', 'lt', 'lt_', 'lu', 'lu_solve', 'map2_', 'map_', 'masked_fill', 'masked_fill_', 'masked_scatter', 'masked_scatter_', 'masked_select', 'matmul', 'matrix_power', 'max', 'mean', 'median', 'min', 'mm', 'mode', 'mul', 'mul_', 'multinomial', 'mv', 'mvlgamma', 'mvlgamma_', 'name', 'names', 'narrow', 'narrow_copy', 'ndim', 'ndimension', 'ne', 'ne_', 'neg', 'neg_', 'nelement', 'new', 'new_empty', 'new_full', 'new_ones', 'new_tensor', 'new_zeros', 'nonzero', 'norm', 'normal_', 'numel', 'numpy', 'orgqr', 'ormqr', 'output_nr', 'permute', 'pin_memory', 'pinverse', 'polygamma', 'polygamma_', 'pow', 'pow_', 'prelu', 'prod', 'put_', 'q_per_channel_axis', 'q_per_channel_scales', 'q_per_channel_zero_points', 'q_scale', 'q_zero_point', 'qr', 'qscheme', 'rad2deg', 'rad2deg_', 'random_', 'real', 'reciprocal', 'reciprocal_', 'record_stream', 'refine_names', 'register_hook', 'reinforce', 'relu', 'relu_', 'remainder', 'remainder_', 'rename', 'rename_', 'renorm', 'renorm_', 'repeat', 'repeat_interleave', 'requires_grad', 'requires_grad_', 'reshape', 'reshape_as', 'resize', 'resize_', 'resize_as', 'resize_as_', 'retain_grad', 'rfft', 'roll', 'rot90', 'round', 'round_', 'rsqrt', 'rsqrt_', 'scatter', 'scatter_', 'scatter_add', 'scatter_add_', 'select', 'set_', 'shape', 'share_memory_', 'short', 'sigmoid', 'sigmoid_', 'sign', 'sign_', 'sin', 'sin_', 'sinh', 'sinh_', 'size', 'slogdet', 'smm', 'softmax', 'solve', 'sort', 'sparse_dim', 'sparse_mask', 'sparse_resize_', 'sparse_resize_and_clear_', 'split', 'split_with_sizes', 'sqrt', 'sqrt_', 'square', 'square_', 'squeeze', 'squeeze_', 'sspaddmm', 'std', 'stft', 'storage', 'storage_offset', 'storage_type', 'stride', 'sub', 'sub_', 'sum', 'sum_to_size', 'svd', 'symeig', 't', 't_', 'take', 'tan', 'tan_', 'tanh', 'tanh_', 'to', 'to_dense', 'to_mkldnn', 'to_sparse', 'tolist', 'topk', 'trace', 'transpose', 'transpose_', 'triangular_solve', 'tril', 'tril_', 'triu', 'triu_', 'true_divide', 'true_divide_', 'trunc', 'trunc_', 'type', 'type_as', 'unbind', 'unflatten', 'unfold', 'uniform_', 'unique', 'unique_consecutive', 'unsqueeze', 'unsqueeze_', 'values', 'var', 'view', 'view_as', 'volatile', 'where', 'zero_']
help(torch.Tensor.view)Help on method_descriptor:
view(...)
view(*shape) -> Tensor
Returns a new tensor with the same data as the :attr:`self` tensor but of a
different :attr:`shape`.
The returned tensor shares the same data and must have the same number
of elements, but may have a different size. For a tensor to be viewed, the new
view size must be compatible with its original size and stride, i.e., each new
view dimension must either be a subspace of an original dimension, or only span
across original dimensions :math:`d, d+1, \dots, d+k` that satisfy the following
contiguity-like condition that :math:`\forall i = d, \dots, d+k-1`,
.. math::
\text{stride}[i] = \text{stride}[i+1] \times \text{size}[i+1]
Otherwise, it will not be possible to view :attr:`self` tensor as :attr:`shape`
without copying it (e.g., via :meth:`contiguous`). When it is unclear whether a
:meth:`view` can be performed, it is advisable to use :meth:`reshape`, which
returns a view if the shapes are compatible, and copies (equivalent to calling
:meth:`contiguous`) otherwise.
Args:
shape (torch.Size or int...): the desired size
Example::
>>> x = torch.randn(4, 4)
>>> x.size()
torch.Size([4, 4])
>>> y = x.view(16)
>>> y.size()
torch.Size([16])
>>> z = x.view(-1, 8) # the size -1 is inferred from other dimensions
>>> z.size()
torch.Size([2, 8])
>>> a = torch.randn(1, 2, 3, 4)
>>> a.size()
torch.Size([1, 2, 3, 4])
>>> b = a.transpose(1, 2) # Swaps 2nd and 3rd dimension
>>> b.size()
torch.Size([1, 3, 2, 4])
>>> c = a.view(1, 3, 2, 4) # Does not change tensor layout in memory
>>> c.size()
torch.Size([1, 3, 2, 4])
>>> torch.equal(b, c)
False