search

DLR-RM / AugmentedAutoencoder

Official Code: Implicit 3D Orientation Learning for 6D Object Detection from RGB Images
MIT License
336 stars 97 forks source link

TypeError running ae_train #79

Closed ghost closed 3 years ago

ghost commented 3 years ago

Hello, thanks for sharing your amazing work.

I was trying to run the ae_train script with a custom.ply object model and a black background for the object orientation. When I run the script I get the following error after loading training and background images

Traceback (most recent call last): File "ae_train.py", line 157, in <module> main() File "ae_train.py", line 114, in main summary_writer = tf.summary.FileWriter(ckpt_dir, sess.graph) File "/home/manuel/Desktop/AugmentedAutoencoder/env/lib/python3.6/site-packages/tensorflow/python/summary/writer/writer.py", line 367, in __init__ filename_suffix) File "/home/manuel/Desktop/AugmentedAutoencoder/env/lib/python3.6/site-packages/tensorflow/python/summary/writer/event_file_writer.py", line 68, in __init__ self._event_queue = six.moves.queue.Queue(max_queue) TypeError: __init__() missing 3 required positional arguments: 'num_threads', 'queue_size', and 'batch_size' I'm using tensorflow 1.14 (installed from requirements.txt).

Any suggestions? Thanks in advance

saqib1707 commented 3 years ago

Hello, I am also facing this same issue. Can someone provide any solution ? TIA

saqib1707 commented 2 years ago

If anyone else is facing this issue: Try building the AAE package first using the setup.py file as mentioned in the README.md. 

pip install --user .

Earlier, I was directly running the ae_train.py using python command.