Wei-1 commented on a change in pull request #12848: Fix Batch input issue with
Scala Benchmark
URL: https://github.com/apache/incubator-mxnet/pull/12848#discussion_r226806945
##########
File path:
scala-package/infer/src/main/scala/org/apache/mxnet/infer/ObjectDetector.scala
##########
@@ -147,13 +150,16 @@ class ObjectDetector(modelPathPrefix: String,
def imageBatchObjectDetect(inputBatch: Traversable[BufferedImage], topK:
Option[Int] = None):
IndexedSeq[IndexedSeq[(String, Array[Float])]] = {
- val imageBatch = ListBuffer[NDArray]()
- for (image <- inputBatch) {
- val scaledImage = ImageClassifier.reshapeImage(image, width, height)
- val pixelsNdarray = ImageClassifier.bufferedImageToPixels(scaledImage,
inputShape)
- imageBatch += pixelsNdarray
- }
- val op = NDArray.concatenate(imageBatch)
+ val inputBatchSeq = inputBatch.toIndexedSeq
+ val imageBatch = inputBatchSeq.indices.par.map(idx => {
+ val scaledImage = ImageClassifier.reshapeImage(inputBatchSeq(idx),
width, height)
Review comment:
`par` will spawn as many threads as the default `ForkJoinThreadPool` size if
there is no other concurrent process.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
