Fix classification example for tensorflow models
authorYuan Zhao <yuanzhao@ti.com>
Thu, 12 Sep 2019 22:06:58 +0000 (17:06 -0500)
committerYuan Zhao <yuanzhao@ti.com>
Fri, 13 Sep 2019 15:32:28 +0000 (10:32 -0500)
commit24a0d91e74955eee8e08150a58993ad7f0b128f5
tree03709bfd574be33061dbbb2515d90ee70ade9358
parent1417d91f33f5a31bdf887974ead1f992f9703b50
Fix classification example for tensorflow models

- Copy original image to show image before pre-processing, because
  pre-processing will change BGR to RGB for tensorflow models
- Subtract 1 from output object class index, because tensorflow outputs
  1001 bytes and uses index-0 for background.  Regular imagenet labels
  only have 1000 entries.
- Fix path to inceptionnet net and params binaries in the config file.
- MCT-1221
examples/classification/main.cpp
examples/classification/readme.md
examples/test/testvecs/config/infer/tidl_config_inceptionNetv1.txt
examples/test/testvecs/config/infer/tidl_config_inceptionNetv1_lg2.txt
examples/test/testvecs/config/tidl_models/tidl_net_inceptionv1_224.bin [moved from examples/test/testvecs/config/tidl_models/tidl_inception_v1_net.bin with 100% similarity]
examples/test/testvecs/config/tidl_models/tidl_param_inceptionv1_224.bin [moved from examples/test/testvecs/config/tidl_models/tidl_inception_v1_param.bin with 100% similarity]