Examples: query, "exact match", wildcard*, wild?ard, wild*rd
Fuzzy search: cake~ (finds cakes, bake)
Term boost: "red velvet"^4, chocolate^2
Field grouping: tags:(+work -"fun-stuff")
Escaping: Escape characters +-&|!(){}[]^"~*?:\ with \, e.g. \+
Range search: properties.timestamp:[1587729413488 TO *] (inclusive), properties.title:{A TO Z}(excluding A and Z)
Combinations: chocolate AND vanilla, chocolate OR vanilla, (chocolate OR vanilla) NOT "vanilla pudding"
Field search: properties.title:"The Title" AND text
Profile picture
AgitatedDove14
Moderator
48 Questions, 8051 Answers
  Active since 10 January 2023
  Last activity 6 months ago

Reputation

0

Badges 1

25 × Eureka!
0 Votes
0 Answers
895 Views
0 Votes 0 Answers 895 Views
4 years ago
0 Votes
0 Answers
891 Views
0 Votes 0 Answers 891 Views
3 years ago
0 Votes
0 Answers
965 Views
0 Votes 0 Answers 965 Views
4 years ago
0 Votes
0 Answers
1K Views
0 Votes 0 Answers 1K Views
New RC for trains-agent is out pip install trains-agent==0.13.2rc1
4 years ago
0 Votes
0 Answers
1K Views
0 Votes 0 Answers 1K Views
docs are up
4 years ago
0 Votes
0 Answers
1K Views
0 Votes 0 Answers 1K Views
YummyWhale40 awesome thanks!
4 years ago
0 Votes
1 Answers
947 Views
0 Votes 1 Answers 947 Views
Gals, Guys & :robot_face: , if you want to checkout the Hyper-Parameters automation (Using Bayesian Optimization Hyper-Band) We have an example on the demo s...
4 years ago
0 Votes
0 Answers
991 Views
0 Votes 0 Answers 991 Views
4 years ago
0 Votes
0 Answers
1K Views
0 Votes 0 Answers 1K Views
New releases: pip install trains==0.13.3https://github.com/allegroai/trains/releases/tag/0.13.3 pip install trains-agent==0.13.2https://github.com/allegroai/...
4 years ago
0 Votes
0 Answers
1K Views
0 Votes 0 Answers 1K Views
https://m.facebook.com/story.php?story_fbid=2484620658505570&id=1620822758218702&refid=52&tn=-R
4 years ago
0 Votes
1 Answers
980 Views
0 Votes 1 Answers 980 Views
Quick note: v1.3.1 caused PipelineDecorator Tasks to by default disable the automagic frameworks connection, this bug is solved in the latest RC pip install ...
2 years ago
0 Votes
0 Answers
1K Views
0 Votes 0 Answers 1K Views
We are at AAAI NY, come look us up :)
4 years ago
0 Votes
2 Answers
1K Views
0 Votes 2 Answers 1K Views
Hi
Hi ClearML v0.17.1 and ClearML-Agent v0.17.0 are now the official packages & repositories 🎉 🎊 👋 🛤️ This new name brings on many changes, mainly replace a...
3 years ago
0 Votes
0 Answers
1K Views
0 Votes 0 Answers 1K Views
https://allegro.ai/docs
4 years ago
0 Votes
0 Answers
1K Views
0 Votes 0 Answers 1K Views
I would guess connectivity issues, the TLS is probably python inaccurate response (I mean in a way, it is also a TLS error, but I would imagine this has more...
4 years ago
0 Votes
0 Answers
1K Views
0 Votes 0 Answers 1K Views
Hi Guys! I have great news, we finally fully implemented support for continuing previously trained models 🎉 Here is a quick example (this is torch, but any ...
4 years ago
0 Votes
0 Answers
1K Views
0 Votes 0 Answers 1K Views
4 years ago
0 Votes
0 Answers
1K Views
0 Votes 0 Answers 1K Views
New video is out 🙂 Cloud Autoscalers are awesome https://www.youtube.com/watch?v=j4XVMAaUt3E
2 years ago
0 Votes
1 Answers
1K Views
0 Votes 1 Answers 1K Views
This is usually due to enterprise level issued https certificates not part of the local installation (basically any python generated SSL request will fail)
4 years ago
0 Votes
0 Answers
1K Views
0 Votes 0 Answers 1K Views
🎊 🍾 Happy new year ! 🎆 🎇 We wanted to thank you all for the great feedback, contribution and general support you guys give us. It is truly fulfilling to ...
3 years ago
0 Votes
3 Answers
508 Views
0 Votes 3 Answers 508 Views
we recently released a new version of clearml-session with Persistent Workspace support! 🚀 🎉 Finally you can develop on remote machines with workspace fold...
7 months ago
0 Votes
0 Answers
1K Views
0 Votes 0 Answers 1K Views
YummyWhale40 you are saying the example code is not working when running with the demo server? Also I think I was able to view your experiment on the demo se...
4 years ago
0 Votes
0 Answers
1K Views
0 Votes 0 Answers 1K Views
Hello Everyone!
4 years ago
0 Votes
0 Answers
1K Views
0 Votes 0 Answers 1K Views
3 years ago
0 Votes
0 Answers
989 Views
0 Votes 0 Answers 989 Views
Gals, Guys & :robot_face: If you want to get some inspiration on building DL Continuous Integration pipelines, I suggest this post (obviously built on top of...
4 years ago
0 Votes
1 Answers
391 Views
0 Votes 1 Answers 391 Views
🙏 Please skip cleaml python package v1.0.1 and just move on to v1.0.2 😊 apologies for the inconvenience 🙂 pip install clearml==1.0.2
3 years ago
0 Votes
1 Answers
462 Views
0 Votes 1 Answers 462 Views
🙏 There is no v1.0 release without a prompt v1.0.1 following it, and we are no different 😊 pip install clearml==1.0.1
3 years ago
0 Votes
1 Answers
497 Views
0 Votes 1 Answers 497 Views
LSTMeow is back! Bots/Gals/Guys feel free to 👍 None
4 years ago
0 Votes
3 Answers
400 Views
0 Votes 3 Answers 400 Views
@<1523703325881536512:profile|ConvolutedSealion94> these are xgboost internal metrics that are automatically picked by clearml
2 years ago
0 Votes
10 Answers
494 Views
0 Votes 10 Answers 494 Views
Happy Friday everyone ! We have a new repo release we would love to get your feedback on 🚀 🎉 Finally easy FRACTIONAL GPU on any NVIDIA GPU 🎊 Run our nvidi...
8 months ago
Show more results questions
0 Are There Python Api Docs For Trains Hosted Anywhere? I'Ve Found Helpful Info In The Class Method Definitions That I Didn'T Find In The Main Docs/Examples

BroadMole98 thank you for noticing !
I'll make sure it is fixed (a few other properties are also missing there, not sure why, I'll ask them to take a look)

3 years ago
0 I'M Having Some Trouble Setting Up My Trains-Server Configuration For Trains. After Copying The Credentials I Get The Following:

FYI:
ssh -R 8080:localhost:8080 -R 8008:localhost:8008 -R 8081:localhost:8081 replace_with_username@ubuntu_ip_heresolved the issue 🙂

3 years ago
0 Hi All, I'M Trying To Deploy Trains On Rancher (Nice Kubernetes Cluster Orchestration Project) Where I'M Quite New To Rancher And Kubernetes. I Have Been Able To Install Trains Using Helm

Maybe the only thing to worry about is making sure the IP address is stable, so if k8s replaces the node, you do not have to reconfigure the clients 🙂

3 years ago
0 Also, I Am Confused About Whether Trains Is Fully Open Source Because I Didn’T See Where The Source For The Web Client Is.

Trains is fully open-source, that said properly publishing and maintaining the web client is still on our to do list (I mean there is totally readable JavaScript code packaged in the trains-server and the dockers). It is constantly pushed because there is generally less contributions on the front-end with these kind of projects. That said of you guys are willing to help, it will greatly help in pushing it forward... LivelyLion31 what do you think, would you guys like to help with the fronte...

4 years ago
0 Hi! Using Pytorchlightning. How Do I Define The Names Of The Plots In The Legend?

I want is to manually provide a name to each series equal to the subject name (Subject 1, Subject 2, etc.)

They appear as they are reported to TB. I think this is a PyTorchLightning thing... If you look as the TB produced, you will get the same naming schemes, no?!

3 years ago
0 Also, I Am Confused About Whether Trains Is Fully Open Source Because I Didn’T See Where The Source For The Web Client Is.

Awesome, PRs are always welcome, and we try to help with any request and feature coming for users. We just added audio support (RC releasing in a few days) based only on users request.
https://github.com/allegroai/trains/issues/120

4 years ago
0 Hi Everyone! Is Anybody Using Log-Scale Parameter Ranges For Hyper-Parameter Optimization? It Seems That There Is A Bug In The Hpbandster Module. I'M Getting Negative Learning Rates..

` from clearml.automation.parameters import LogUniformParameterRange
sampler = LogUniformParameterRange(name='test', min_value=-3.0, max_value=1.0, step_size=0.5)
sampler.to_list()

Out[2]:
[{'test': 1.0},
{'test': 3.1622776601683795},
{'test': 10.0},
{'test': 31.622776601683793},
{'test': 100.0},
{'test': 316.22776601683796},
{'test': 1000.0},
{'test': 3162.2776601683795}] `

2 years ago
0 Currently, To Provide Ssh Access To The Docker Images For A Task,

Hmm you either need to run with SUDO or make sure the running user has docker run permissions

3 years ago
0 Hi, I Am Trying To Upload A Plot To An Existing Task Using The

SmarmyDolphin68 if you can reproduce the behavior in a standalone script , it will really accelerate fixing this issue

3 years ago
0 Hi! I'M Running Launch_Multi_Mode With Pytorch-Lightning

Hi @<1578555761724755968:profile|GrievingKoala83>

Two tasks are created, but the training does not begin, both tasks are in perpetual running.

Can you print something after the task.launch_multi_node(args.nodes)) - I'm assuming the two Tasks are running and are blocked on the " Trainer " class

If specified

args.gpus=2

and args.nodes=2,

three

tasks are created.

This is really odd, can you add some prints with task id and rank after the ...

4 months ago
0 Hello, Everyone, Just Wanted To Ask, How We Can Fix The Following Issue:

Hi @<1657918706052763648:profile|SillyRobin38>
You should either disable certificate verification or add the self-signed certificate to your urllib
None
or set

export REQUESTS_CA_BUNDLE="/path/to/cert/file"
export SSL_CERT_FILE="/path/to/cert/file"
4 months ago
0 Is There Any Way To Clear The Installed Packages Of A Task Programmatically? (I.E. Using The Python Sdk And Not The Ui)

Regrading resetting it via code, if you need I can write a few lines for you to do that , although that might be a bit hacky.
Maybe we should just add a flag saying, use requirements.txt ?
What do you think?

3 years ago
0 Is There Any Way To Clear The Installed Packages Of A Task Programmatically? (I.E. Using The Python Sdk And Not The Ui)

Hi GiddyTurkey39
Are you referring to an already executed Task or the current running one?
(Also, what is the use case here? is it because the "installed packages are in accurate?)

3 years ago
0 Hi

Hmm make sense, then I would call the export_task once (kind of the easiest to get the entire Task object description pre-filled for you) with that, you can just create as many as needed by calling import_task.
Would that help?

3 years ago
0 Hi All, I'M Trying To Deploy Trains On Rancher (Nice Kubernetes Cluster Orchestration Project) Where I'M Quite New To Rancher And Kubernetes. I Have Been Able To Install Trains Using Helm

WickedGoat98

I will try to collect the installation steps in a document and share it to the community once ready

Thank you! this will be awesome !

We're here if you need anything 🙂

3 years ago
4 years ago
0 Is There Any Simple Way To Orchestrate A Batch To Train A Model With Different Features (In Order To Do Feature Selection, For Example) Through A Single .Py File? I Saw The Following Example

Correct, but do notice that (1) task names are not unique and you can change them after the Task was executed (2) when you clone the Task, you can actually rename it, when an agent is running the Task, basically the init function is ignored, because the Task already exists. Make sense ?

2 years ago
0 Hi There, I’Ve Been Trying To Play Around With The Model Inference Pipeline Following

Also what do you have in the "Configuration" section of the serving inference Task?

one year ago
0 Hello, I'M Getting This Weird Error From Time To Time When Running A Pipeline, It Add My Tasks As Drafts But Never Launch Them, When I Checked The Logs, I See The Following ;

BulkyTiger31 could it be there is some issue with the elastic container ?
Can you see any experiment's metrics ?

2 years ago
0 Hi All. I Am Wondering How People Tend To Use Clearml With Cross-Validation. Do You Tend To Create Separate Experiments For Each Fold? And If So, Would You Then Create Another Experiment For The Aggregated Results?

Hi RattyBat71

Do you tend to create separate experiments for each fold?

If you really want to parallelized the workload, then splitting it to multiple executions (i.e. passing an argument of the index of the same CV) makes sense, then you can compare / sort the results based on a specific metric. That said if speed is not important, just having a single script with multiple CVs might be easier to implement?!

one year ago
0 Is There Any Difference In:

Hi HelplessCrocodile8
yes there is:
in the first case, the new_key will be automatically logged:
a_dict = {} a_dict = task.connect(a_dict) a_dict['new_key'] = 42In the second example changes to the "object" passed to connect are not tracked
make sense ?

3 years ago
0 Hi

Hi SmugTurtle78
Unfortunately there is no actual filtering for these logs, because they are so important for debugging and visibility. I have to ask, what's the use case to remove some of them ?

one year ago
0 Is There Any Difference In:

btw: I'm assuming that args is not the ArgParser object, as the ArgParser is automatically "connected" ?

3 years ago
3 years ago
0 Hello Everyone, I’M Newcomer For Clearml. I Have Question Related To

I do not think this is the upload timeout, it makes no sense to me for GCP package (we do not pass any timeout, it's their internal default for the argument) to include a 60sec timeout for upload...
I'm also not sure where is the origin of the timeout (I'm assuming the initial GCP handshake connection could not actually timeout, as the response should be relatively quick, so 60sec is more than enough)

3 years ago
Show more results compactanswers