From: 이상규/On-Device Lab(SR)/Principal Engineer/삼성전자 <sg5.lee@samsung.com>
Date: Fri, 16 Aug 2019 04:28:12 +0000 (+0900)
Subject: [nnpackage_run] Fix wrong allocation size for output (#6640)
X-Git-Tag: accepted/tizen/unified/20190903.052428~360
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=7f466e438f1ad28fd016965d801641b0eabc037b;p=platform%2Fcore%2Fml%2Fnnfw.git

[nnpackage_run] Fix wrong allocation size for output (#6640)

outputs[i] is vector<float>. sizeof(float) should not be multiplied.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
---

diff --git a/tests/tools/nnpackage_run/src/nnpackage_run.cc b/tests/tools/nnpackage_run/src/nnpackage_run.cc
index 862ab90..9a6383a 100644
--- a/tests/tools/nnpackage_run/src/nnpackage_run.cc
+++ b/tests/tools/nnpackage_run/src/nnpackage_run.cc
@@ -111,7 +111,7 @@ int main(const int argc, char **argv)
     for (uint32_t j = 0; j < ti.rank; ++j)
       output_num_elements *= ti.dims[j];
 
-    outputs[i].resize(sizeof(float) * output_num_elements);
+    outputs[i].resize(output_num_elements);
     NNPR_ENSURE_STATUS(nnfw_set_output(session, i, NNFW_TYPE_TENSOR_FLOAT32, outputs[i].data(),
                                        sizeof(float) * output_num_elements));
   }