[GNA] fixed conversion from fp16 to fp32 networks in case of const blobs (#2446)
authorEugene Smirnov <eugene.smirnov@intel.com>
Tue, 29 Sep 2020 16:44:12 +0000 (19:44 +0300)
committerGitHub <noreply@github.com>
Tue, 29 Sep 2020 16:44:12 +0000 (19:44 +0300)
commitfecc7eac908ee5efe3305a777a6afdf8053a7834
treea2095ad67c766ddb381d0d117a0df11488ab55d5
parent266d275293a20016330a4f3ac1ba0d22c164945b
[GNA] fixed conversion from fp16 to fp32 networks in case of const blobs (#2446)
inference-engine/src/gna_plugin/frontend/weights_converter.hpp
inference-engine/tests/functional/plugin/gna/shared_tests_instances/single_layer_tests/fake_quantize.cpp