Kiriti Gowda
Kiriti Gowda
@Sfinx using TOT master ``` ./mv_build/mvobjdetect /opt/rocm/share/mivisionx/samples/mv_objdetect/data/images/img_04.JPG - --install_folder . --bb 20 0.2 0.4 --v Success::loading deployment library ./lib/libmv_deploy.so Config_input:::data Config_output:::conv9 OK: loaded 39 kernels from libvx_nn.so OK: OpenVX using...
@Sfinx are you using mivisionx source build or package? @LakshmiKumar23 can you try to reproduce this issue?
@Sfinx any updates on this? Did the master work for you?
@Sfinx -- could you try with the updated instructions - https://github.com/ROCm/MIVisionX/tree/master/samples/mv_objdetect#sample---detection-using-pre-trained-caffe-model
@Sfinx - this change is required to find half - https://github.com/ROCm/MIVisionX/commit/01e112c70779ceb2c909f0c7e2e926729b117d92 -- This is missing in the 5.5 release If you add this patch to your local build, the app...
Upgrading to `sudo pip3 install protobuf==3.20.2 onnx==1.13.0` seems to work better. @hansely needs to verify. @paveltc need to test.
@hansely ONNX deps for 1.11.0 is different from 1.13.0, these deps are common for caffe & ONNX.
Hi @hansely any thoughts on this?
Use `future-0.18.3`
@hansely can we close this issue?