New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[App]: No Selected Runs have Saved Code #7426
Comments
In case it's useful to anyone stumbling upon this same issue, I've just been using this as a workaround to compare code for now: def compare_runs(run_id_a: str, run_id_b: str,):
import tempfile
import os
import subprocess
with tempfile.TemporaryDirectory() as tmp_dir:
api = wandb.Api()
code_dirs = []
for run_id in [run_id_a, run_id_b]:
run = api.run(run_id)
code_artifacts = [x for x in run.logged_artifacts() if x.type == "code"]
if len(code_artifacts) == 0:
raise ValueError(f"No code artifacts found for run {run_id}")
elif len(code_artifacts) > 1:
print(f"Multiple code artifacts found for run {run_id}, taking first.")
code = code_artifacts[0]
# download to temporary directory
code_dir = code.download(root=os.path.join(tmp_dir, run_id))
code_dirs.append(code_dir)
subprocess.call(
["diff", "-r", code_dirs[0], code_dirs[1]]
) But it would be great to visualize the code the in interface |
Jason Davenport commented: Thank you for reaching out and our apologies on the delayed response. Let me look into this deeper and see if I can reproduce it on my end. If this ends up being a bug I will let you know once it has been reported and any additional steps if needed. Looking forward to working with you and I hope you are having a great start to the week! Best, |
Jason Davenport commented: Wanted to give you a quick update. It looks like this is a known issue that engineering is actively working on. We will reach out if there is any more information we need; otherwise, keep an eye out as we will let you know when the issue has been resolved! Hope you have a great rest of the week! Best, |
Current Behavior
I see the following error message when trying to compare code across runs, even though the selected runs do indeed have saved code
Expected Behavior
I'd expect something to show up in the panel
Steps To Reproduce
I'm logging code using
Environment
OS: Mac
Browsers: Arc
Version:
The text was updated successfully, but these errors were encountered: