Dogukan Altay

The model is not reliable enough to use. Even if you put a 1x1 pixel input, it can produce 90%> results.

I think this repo is no longer maintained by the authors of the papers. In my humble opinion, solving the true class order is impossible for the kinetics and other...

@Jimmy880 You really dig this issue out of the grave thanks a lot!

The same error occured for me too. Generally when I publish absolute ground truth(gazebo model state) UAV ossilates for a while and lose control and gives preflight check errors. It...

I am trying to achieve same as well. With EKF2_AID_MASK=1(GPS only) it works as intended but the type_masks in the Mavlink documentation not working. However, if you are trying to...

I managed to run the code with the given model. You can use the below script. However, Im not 100% sure this is the right way to do. ``` def...

That error caused by feeding 4-channel images to the network. You can solve the problem with the following fix. **In helper.py, after line 161 you should add line below:** ```...

Update: I have resolved the problem. The reason is that, I am using a tensorflow implementation of Mobilenet SSDv2. Therefore after the conversion with the openvino model optimizer, the input...

From https://software.intel.com/en-us/articles/transitioning-from-intel-movidius-neural-compute-sdk-to-openvino-toolkit : ``` Multiple NCS Devices The NCSDK provided an API to enumerate all NCS devices in the system and let the application programmer run inferences on specific devices....

I am encountering the same error as well. However, the crash is much more random in my case. It can be anytime during my simulations. Trying to investigate the issue...