org.bytedeco.pytorch

Class MNIST

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.pytorch.MNISTBatchDataset

org.bytedeco.pytorch.MNISTDataset

org.bytedeco.pytorch.MNIST

All Implemented Interfaces:

AutoCloseable

@Namespace(value="torch::data::datasets")
 @NoOffset
 @Properties(inherit=torch.class)
public class MNIST
extends MNISTDataset

The MNIST dataset.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	MNIST.Mode The mode in which the dataset is loaded.

Nested classes/interfaces inherited from class org.bytedeco.javacpp.Pointer

Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter

Field Summary

Fields inherited from class org.bytedeco.pytorch.MNISTBatchDataset

is_stateful

Fields inherited from class org.bytedeco.javacpp.Pointer

address, capacity, limit, position

Constructor Summary

Constructors

Constructor and Description
MNIST(BytePointer root)
MNIST(BytePointer root, MNIST.Mode mode) Loads the MNIST dataset from the root path.
MNIST(Pointer p) Pointer cast constructor.
MNIST(String root)
MNIST(String root, int mode)

Method Summary

Modifier and Type	Method and Description
Example	get(long index) Returns the Example at the given index.
Tensor	images() Returns all images stacked into a single tensor.
boolean	is_train() Returns true if this is the training subset of MNIST.
SizeTOptional	size() Returns the size of the dataset.
Tensor	targets() Returns all targets stacked into a single tensor.

Methods inherited from class org.bytedeco.pytorch.MNISTDataset

get_batch, get_batch

Methods inherited from class org.bytedeco.pytorch.MNISTBatchDataset

is_stateful, map

Methods inherited from class org.bytedeco.javacpp.Pointer

address, asBuffer, asByteBuffer, availablePhysicalBytes, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, formatBytes, free, getDirectBufferAddress, getPointer, getPointer, getPointer, getPointer, hashCode, interruptDeallocatorThread, isNull, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetAddress, offsetof, offsetof, parseBytes, physicalBytes, physicalBytesInaccurate, position, position, put, realloc, referenceCount, releaseReference, retainReference, setNull, sizeof, sizeof, toString, totalBytes, totalCount, totalPhysicalBytes, withDeallocator, zero

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

MNIST

public MNIST(Pointer p)

Pointer cast constructor. Invokes Pointer(Pointer).

MNIST

public MNIST(@StdString
             BytePointer root,
             MNIST.Mode mode)

Loads the MNIST dataset from the root path. The supplied root path should contain the *content* of the unzipped MNIST dataset, available from http://yann.lecun.com/exdb/mnist.

MNIST

public MNIST(@StdString
             BytePointer root)

MNIST

public MNIST(@StdString
             String root,
             @Cast(value="torch::data::datasets::MNIST::Mode")
             int mode)

MNIST

public MNIST(@StdString
             String root)

Method Detail

get

@ByVal
public Example get(@Cast(value="size_t")
                          long index)

Returns the Example at the given index.

Overrides:

get in class MNISTDataset

size

@ByVal
public SizeTOptional size()

Returns the size of the dataset.

Overrides:

size in class MNISTBatchDataset

is_train

@Cast(value="bool")
 @NoException(value=true)
public boolean is_train()

Returns true if this is the training subset of MNIST.

images

@Const
 @ByRef
public Tensor images()

Returns all images stacked into a single tensor.

targets

@Const
 @ByRef
public Tensor targets()

Returns all targets stacked into a single tensor.