torta24x

As of now I have found two reasons for Inf loss value either during train or validation 1. Higher learning rate : try reducing learning rate , say do 1/10th...

Refer to this Issue: https://github.com/Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB/issues/182#issuecomment-915404168 Hope this helps

Got it here - https://github.com/markshih91/mobilenet_v2_ssdlite_keras/issues/6#issuecomment-739324354

Solution : Weirdly I have to comment out bellow line in ``makefile.config`` to make it work. It worked for now but I am not sure of the future consequences. I...

> @torta24x Which CUDA and cuDNN version are you using? I've tested it with CUDA 10.2 and cuDNN 8.0.0.180. My bad, actually the cuDNN was not installed, will be installing...

I found these version and some basic code modification is [THIS](https://github.com/rui-liu/mobilenet_v2_ssdlite_keras/commits/master) repo which is a fork of this repo. keras==2.3.1 tensorflow-gpu==2.1.0 opencv==3.4.2 pydot==1.4.1 scikit-learn==0.22.1 pillow==7.0.0 tqdm==4.42.1 beautifulsoup4==4.8.2 imageio==2.6.1 matplotlib=3.1.3

This is a required feature, we are looking for the same feature. Any update ?