Bedapudi Praneeth
Bedapudi Praneeth
I updated the code with almost same as pre-processing as web version. tried to match it wherever possible. result scores seem to be very close (but not exactly same). One...
@AlexUrrutia wait 10 min to start your testing. the new docker container based on 3.0.8 is being pushed.
yupp, it has false positives sometimes. I am also training a bigger model which will have better accuracy. Will update the repo in couple of days.
@NasaKHw can you reproduce in a colab and share the link?
https://colab.research.google.com/
Hey, please create a new clean python 3.10 conda environment and run `pip install --upgrade nudenet` and try the same and paste here what's the output you got.
@CortesJoan this requires a newer different type of model which I am working on. the current models will only detect the full breast/ chest area, so it cant be done...
Check if tensorflow can use gpu.
All this information is a trivial google search away. I am happy to help if there are any problems with txt2txt. EDIT: https://datascience.stackexchange.com/questions/23895/multi-gpu-in-keras
What are your tf, keras versions and python version. Also post the exact error and other logs you are getting.