package torch

You can search for identifiers within the package.

in-package search v0.2.0

PyTorch bindings for OCaml

Install

Dune Dependency

github.com Readme Edit opam file Versions (18)

Authors

L

Laurent Mazare

Maintainers

L

Laurent Mazare <lmazare@gmail.com>

Sources

0.4.tar.gz

md5=9547e9e025dacd52e405ff699539c582

sha512=23fd9bef6f5f11c55171f2383a2f7ca57330511af6521a4579410e002d8667a91e764aecc2deb1cf8d7bf3b0e988cd3020850fa4a5a1ec713dfb110ec7352892

doc/torch.vision/Torch_vision/Image/index.html

Module `Torch_vision.Image`Source

Source

val load_image : 
  ?resize:(Base.int * Base.int) ->
  Base.string ->
  Torch.Tensor.t Base.Or_error.t

load_image ?resize filename returns a tensor containing the pixels for the image in filename. Supported image formats are JPEG and PNG. The resulting tensor has dimensions NCHW (with N = 1). When resize is set, the image is first resized preserving its original ratio then a center crop is taken.

Source

val load_images : 
  ?resize:(Base.int * Base.int) ->
  Base.string ->
  Torch.Tensor.t

load_images ?resize dir_name is similar to applying load_image to all the images in dir_name. The resulting tensor has dimensions NCHW where N is the number of images.

Source

val load_dataset : 
  dir:Base.string ->
  classes:Base.string Base.list ->
  with_cache:Base.string Base.option ->
  resize:(Base.int * Base.int) ->
  Torch.Dataset_helper.t

Sourceval write_image : Torch.Tensor.t -> filename:Base.string -> Base.unit

Sourcemodule Loader : sig ... end

package torch

Install

Dune Dependency

Authors

Maintainers

Sources

doc/torch.vision/Torch_vision/Image/index.html

Module Torch_vision.ImageSource

Module `Torch_vision.Image`Source