Tomas

@jiegzhan yes, model-2700 files do exist. but there is no model-2700 file as such nor it's a directory: ls -lrt ./checkpoints_1486165230/ total 71404 -rw-r--r-- 1 root root 1433 Feb 3...

python3 -c 'import tensorflow as tf; print(tf.__version__)' I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcublas.so locally I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcudnn.so locally I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcufft.so...

Do you get more files created in checkpoints directory? I see *.meta, *.index, *.data-* and checkpoint.

Found this: https://github.com/tensorflow/tensorflow/blob/master/RELEASE.md New checkpoint format becomes the default in tf.train.Saver. Old V1 checkpoints continue to be readable; controlled by the write_version argument, tf.train.Saver now by default writes out in...

Yep, testing it with V1 now.

Yep, works fine with : saver = tf.train.Saver(tf.all_variables(), write_version=tf.train.SaverDef.V1) This is the how the warning message looks like: WARNING:tensorflow:******************************************************* WARNING:tensorflow:******************************************************* WARNING:tensorflow:TensorFlow's V1 checkpoint format has been deprecated. WARNING:tensorflow:TensorFlow's V1 checkpoint...

I also tried the example from README.md, but it seems to get stuck: ``` Working Agent: Researcher Starting Task: Investigate the latest AI trends ... > Entering new AgentExecutor chain......

I've encountered a similar issue and would like to add some observations for clarity: 1. Upon experiencing the delay, I've found that if I wait approximately 10 seconds, the new...