First forgive me if these questions are childish. I Searched google for answers but failed, so I came here.
I am trying to set up TensorFlow development environment to contribute to opensource TensorFlow. let me first explain what I did so that I can explain my question better.
first I forked TensorFlow and cloned it into my local machine.
pulled the docker file tensorflow/build:2.15-python3.10 and started it in my docker.
mounted the TensorFlow working directory to the docker container with the following command:
docker run -it --rm -v $PWD:/tmp -w /tmp tensorflow/build:2.15-python3.10
now in the docker container ran the following command to test a specific target:
Bazel test tensorflow/python/kernel_tests/nn_ops:softmax_op_test
Bazel started executing with the following info:
INFO: Analyzed 2 targets (604 packages loaded, 41543 targets configured).
INFO: Found 2 test targets…
Now let me come to my question. I have a low spec pc and it seems the task will take at least 10 hours. and if I exit with ctrl + c and start again the task starts from the beginning
- is there any way to pause and resume Bazel actions so that I can resume again from where I left off?
- after the actions are complete if I stop the running docker container and run it again later will Bazel start from beginning like it is doing now.