external_source(source=None, num_outputs=None, *, cycle=None, name=None, device='cpu', layout=None, dtype=None, ndim=None, cuda_stream=None, use_copy_kernel=None, batch=True, **kwargs)¶
Creates a data node which is populated with data from a Python source. The data can be provided by the
sourcefunction or iterable, or it can be provided by
pipeline.feed_input(name, data, layout, cuda_stream)inside
In the case of the GPU input, it is the user responsibility to modify the provided GPU memory content only using provided stream (DALI schedules a copy on it and all work is properly queued). If no stream is provided feeding input blocks until the provided memory is copied to the internal buffer.
nvidia.dali.fn.external_source()operator is partially compatible with TensorFlow integration via
nvidia.dali.plugin.tf.experimental.DALIDatasetWithInputs(). Please refer to its documentation for details.
To return a batch of copies of the same tensor, use
nvidia.dali.types.Constant(), which is more performant.
source (callable or iterable) –
The source of the data.
The source is polled for data (via a call
next(source)) when the pipeline needs input for the next iteration. Depending on the value of
num_outputs, the source can supply one or more data items. The data item can be a whole batch (default) or a single batch entry (when
num_outputsis not set, the
sourceis expected to return one item (a batch or a sample). If this value is specified (even if its value is 1), the data is expected to a be tuple, or list, where each element corresponds to respective return value of the external_source.
The data samples must be in one of the compatible array types:
NumPy ndarray (CPU)
MXNet ndarray (CPU)
PyTorch tensor (CPU or GPU)
CuPy array (GPU)
DALI Tensor object
Batch sources must produce entire batches of data. This can be achieved either by adding a new outermost dimension to an array or by returning a list of arrays (in which case they can be of different size, but must have the same rank and element type). A batch source can also produce a DALI TensorList object, which can be an output of another DALI pipeline.
A per-batch source may accept one positional argument. If it does, it is the index of current iteration within epoch and consecutive calls will be
source(1), and so on. If batch_info is set to True, instance of
nvidia.dali.types.BatchInfowill be passed to the source, instead of a plain index.
A per-sample source may accept one positional argument of type
nvidia.dali.types.SampleInfo, which contains index of the sample in current epoch and in the batch, as well as current iteration number.
If the source is a generator function, the function is invoked and treated as an iterable. However, unlike a generator, the function can be used with
cycle. In this case, the function will be called again when the generator reaches the end of iteration.
For GPU inputs, it is a user’s responsibility to modify the provided GPU memory content only in the provided stream. DALI schedules a copy on this stream, and all work is properly queued. If no stream is provided, DALI will use a default, with a best-effort approach at correctness. See the
cuda_streamargument documentation for more information.
num_outputs (int, optional) –
If specified, denotes the number of TensorLists that are produced by the source function.
If set, the operator returns a list of
DataNodeobjects, otherwise a single
DataNodeobject is returned.
- Keyword Arguments
cycle (string or bool, optional) –
Specifies if and how to cycle through the source. It can be one of the following values:
None- don’t cycle;
StopIterationis raised when end of data is reached; this is the default behavior
True- the data is repeated indefinitely,
"raise"- when the end of data is reached,
StopIterationis raised, but the iteration is restarted on subsequent call.
This flag requires that the
sourceis a collection, for example, an iterable object where
iter(source)returns a fresh iterator on each call, or a generator function. In the latter case, the generator function is called again when more data than was yielded by the function is requested.
"raise"can be used with DALI iterators to create a notion of epoch.
name (str, optional) –
The name of the data node.
Used when feeding the data in
iter_setupand can be omitted if the data is provided by
layout (layout str or list/tuple thereof, optional) –
If provided, sets the layout of the data.
num_outputs > 1, the layout can be a list that contains a distinct layout for each output. If the list has fewer than
num_outputselements, only the first outputs have the layout set, the rest of the outputs don’t have a layout set.
dtype (nvidia.dali.types.DALIDataType or list/tuple thereof, optional) –
Input data type.
num_outputs > 1, the
dtypecan be a list that contains a distinct value for each output.
The operator will validate that the fetched data is of the provided type. If the argument is omitted or
DALIDataType.NO_TYPEis passed, the operator will infer the type from the provided data.
This argument will be required starting from DALI 2.0.
ndim (int or list/tuple thereof, optional) –
Number of dimensions in the input data.
num_outputs > 1, the
ndimcan be a list that contains a distinct value for each output.
The dimensionality of the data provided to the operator will be verified against this value. Number of dimensions can be also inferred from the
layoutargument if provided.
layoutargument is provided, the
ndimmust match the number of dimensions in the layout.
Specifying the input dimensionality will be required starting from DALI 2.0
cudaStream_tor an object convertible to
torch.cuda.StreamThe CUDA stream is used to copy data to the GPU or from a GPU source.
If this parameter is not set, a best-effort will be taken to maintain correctness. That is, if the data is provided as a tensor/array from a recognized library such as CuPy or PyTorch, the library’s current stream is used. Although this approach works in typical scenarios, with advanced use cases, and code that uses unsupported libraries, you might need to explicitly supply the stream handle.
This argument has two special values:
0 - Use the default CUDA stream
1 - Use DALI’s internal stream
If internal stream is used, the call to
feed_inputwill block until the copy to internal buffer is complete, since there’s no way to synchronize with this stream to prevent overwriting the array with new data in another stream.
use_copy_kernel (bool, optional) –
If set to True, DALI will use a CUDA kernel to feed the data instead of cudaMemcpyAsync (default).
This is applicable only when copying data to and from GPU memory.
blocking (bool, optional) – Determines whether the external source should wait until data is available or just fail when the data is not available.
no_copy (bool, optional) –
Determines whether DALI should copy the buffer when feed_input is called.
If set to True, DALI passes the user memory directly to the pipeline, instead of copying it. It is the user responsibility to keep the buffer alive and unmodified until it is consumed by the pipeline.
The buffer can be modified or freed again after the output of the relevant iterations has been consumed. Effectively, it happens after Pipeline’s
cpu_queue_depth * gpu_queue_depth(when they are not equal) iterations following the
The memory location must match the specified
deviceparameter of the operator. For the CPU, the provided memory can be one contiguous buffer or a list of contiguous Tensors. For the GPU, to avoid extra copy, the provided buffer must be contiguous. If you provide a list of separate Tensors, there will be an additional copy made internally, consuming both memory and bandwidth.
Automatically set to
batch (bool, optional) –
If set to True or None, the
sourceis expected to produce an entire batch at once. If set to False, the
sourceis called per-sample.
parallelto True automatically sets
batchto False if it was not provided.
batch_info (bool, optional, default = False) – Controls if a callable
sourcethat accepts an argument and returns batches should receive
BatchInfoinstance or just an integer representing the iteration number. If set to False (the default), only the integer is passed. If
sourceis not callable, does not accept arguments or
batchis set to False, setting this flag has no effect.
parallel (bool, optional, default = False) –
If set to True, the corresponding pipeline will start a pool of Python workers to run the callback in parallel. You can specify the number of workers by passing
py_num_workersinto pipeline’s constructor.
parallelis set to True, samples returned by
sourcemust be NumPy/MXNet/PyTorch CPU arrays or TensorCPU instances.
Acceptable sources depend on the value specified for
batchis set to
a callable (a function or an object with
__call__method) that accepts exactly one argument (
SampleInfoinstance that represents the index of the requested sample).
batchis set to
sourcecan be either:
a callable that accepts exactly one argument (either
BatchInfoinstance or an integer - see
a generator function.
batchvalue, callables should be stateless - they should produce requested sample or batch solely based on the
BatchInfoinstance or index in batch, so that they can be run in parallel in a number of workers.
sourcecallback must raise a
StopIterationwhen the end of the data is reached. Note, that due to prefetching, the callback may be invoked with a few iterations past the end of dataset - make sure it consistently raises a
StopIterationin that case.
sourcecan be run in parallel by multiple workers. For
batch=Truemultiple batches can be prepared in parallel, with
batch=Falseit is possible to parallelize computation within the batch.
batch=True, callables performance might especially benefit from increasing
prefetch_queue_depthso that a few next batches can be computed in parallel.
Iterator or generator function will be assigned to a single worker that will iterate over them. The main advantage is execution in parallel to the main Python process, but due to their state it is not possible to calculate more than one batch at a time.
prefetch_queue_depth (int, option, default = 1) – When run in
parallel=Truemode, specifies the number of batches to be computed in advance and stored in the internal buffer, otherwise parameter is ignored.