search

bitsauce / Carla-ppo

This repository hosts a customized PPO based agent for Carla. The goal of this project is to make it easier to interact with and experiment in Carla with reinforcement learning based agents -- this, by wrapping Carla in a gym like environment that can handle custom reward functions, custom debug output, etc.
MIT License
229 stars 56 forks source link

module 'tensorflow' has no attribute 'AUTO_REUSE' #26

Open nsliem745 opened 1 year ago

nsliem745 commented 1 year ago

File "run_eval.py", line 16, in from vae.models import ConvVAE, MlpVAE File "C:\CARLA_0.9.13\PythonAPI\examples\Trials\RL\Carla-ppo\vae\models.py", line 33, in class VAE(): File "C:\CARLA_0.9.13\PythonAPI\examples\Trials\RL\Carla-ppo\vae\models.py", line 40, in VAE model_dir=".", loss_fn=bce_loss, training=True, reuse=tf.AUTO_REUSE, AttributeError: module 'tensorflow' has no attribute 'AUTO_REUSE'

merkol commented 1 year ago

You may have installed tensorflow.v2 use v1 instead or call it like this tf.compat.v1.AUTO_REUSE