Hey,
I am trying to use the deepview ModelClient API to run a CNN at inference. Because right now I am at first trying to run this on the local host, the later chip technology is trivial to mention. I ran the deeplab_v3 segmentation example and it worked. However, loading my CNN fails with the error-msg: " 'error': 'model load error' ". The code is actually (in minimal form) just calling
from deepview.rt.modelclient import ModelClient
modelclient = ModelClient("http://127.0.0.1:10818/v1", path_to_rtm)
As mentioned, is path_to_rtm the deelab_v3 model from the example folder the code runs through without errors. If path_to_rtm is my CNN (Converted using the eIQ interface from .h5 as well as from .tflite to .rtm) leading to the mentioned error.
Do you have any idea why it isnt working, although the conversion(using th eIQ Toolkit) of my CNN to .rtm ran without errors ?
Would be very happy about any hints.
