5,323
edits
No edit summary |
|||
Line 38: | Line 38: | ||
==Usage== | ==Usage== | ||
Note that there are some useful functions under <code>torch.nn.functional</code> which is typically imported as <code>F</code>. | |||
===torch.meshgrid=== | ===torch.meshgrid=== | ||
Note that this is transposed compared to <code>np.meshgrid</code>. | Note that this is transposed compared to <code>np.meshgrid</code>. | ||
===torch. | ===torch.multinomial=== | ||
[https://pytorch.org/docs/stable/ | [https://pytorch.org/docs/stable/generated/torch.multinomial.html torch.multinomial]<br> | ||
====F.grid_sample | If you need to sample with a lot of categories and with replacement, it may be faster to use `torch.cumsum` to build a CDF and `torch.searchsorted`. | ||
{{hidden | torch.searchsorted example | | |||
<syntaxhighlight lang="python"> | |||
# Create your weights variable. | |||
weights_cdf = torch.cumsum(weights, dim=0) | |||
weights_cdf_max = weights_cdf[0] | |||
sample = torch.searchsorted(weights_cdf, | |||
weights_cdf_max * torch.rand(num_samples)) | |||
</syntaxhighlight> | |||
}} | |||
===F.grid_sample=== | |||
[https://pytorch.org/docs/stable/nn.functional.html#grid-sample Doc]<br> | [https://pytorch.org/docs/stable/nn.functional.html#grid-sample Doc]<br> | ||
This function allows you to perform interpolation on your input tensor.<br> | This function allows you to perform interpolation on your input tensor.<br> | ||
Line 108: | Line 121: | ||
Note that [https://en.wikipedia.org/wiki/Bfloat16_floating-point_format <code>bfloat16</code>] is different from IEEE float16. bfloat16 has fewer mantissa bits (8 exp, 7 mantissa) and is used by Google's TPUs. In contrast, float16 has 5 exp and 10 mantissa bits. | Note that [https://en.wikipedia.org/wiki/Bfloat16_floating-point_format <code>bfloat16</code>] is different from IEEE float16. bfloat16 has fewer mantissa bits (8 exp, 7 mantissa) and is used by Google's TPUs. In contrast, float16 has 5 exp and 10 mantissa bits. | ||
==Classification== | ==Classification== |