CostlyOstrich36

0 Questions, 4172 Answers

Active since 10 January 2023

Last activity 2 years ago

Reputation

Answers 4172

0 Hey, About The Dependency Propagation Of Pipeline Components, If I Call A Vanilla Python Function From A Component Does The Dependencies Specified In The Internal Imports Propagated To This Function Call Too ? And Additionally If That Function Is In Anoth

Hi FierceHamster54 , can you please elaborate on the process with a more specific example?

2 years ago

0 Logger = Logger.Current_Logger() Logger.Report_Media( Title="Test", Series="Audio", Local_Path="/Path/To/File.Wav", Iteration=1, Max_History=-1 )

However, now when I go in the Results -> Debug Samples tab, the s3 credential window pops up. Every time that I refresh the page

RattyLouse61 , What version of ClearML are you running, I think this issue was solved in 1.3.0 release

3 years ago

0 Hi, I Noted That If I Run My Codes On My Laptop With Remote_Execute Off A Python3.8 Venv, And When The Remote Task Starts Executing But The Image Is Installed With A Different Version Of Python, Say Python3.8, We Would Encounter Errors With Venv. At This

SubstantialElk6 , the agent is designed to re-run in an environment as close as possible to the original. Can you please provide logs of the two experiments so we can compare? I'm not sure what the issue is. Do both computers have the same python versions?

3 years ago

0 Clearml Provides Api'S To Create Pipelines And Deploy Models ?

And regarding model deployment you mean serving the model through a serving engine such as triton?

3 years ago

0 Hello Guys, I Got This Error On My Pipeline Execution When Processing Data For Model Training. There Are About 10 Steps, But This Errors Occured When It Reaches Step 7

Hi MoodyCentipede68 ,

What version of ClearML / ClearML-Agent are you using? Is it a self hosted server or the SaaS?
Also, can you explain what step 7 was trying to do? Is it running locally or distributed?

3 years ago

0 Hey, Can Clearml Uploads Data To Private Blob Storage Azure? I Have Authorization Errors. Is It Due To The Fact That I Do Not Have The Required Permission On The Storage Account (Could Be Possible) Or The Fact That The Storage Account Is Set As Private A

@<1556812486840160256:profile|SuccessfulRaven86> , I think this is because you don't have the proper permissions 🙂

2 years ago

0 Hi, Is There Any Document About Migration Clearml-Server. Currently, I Have Clearml-Server Running On Servera But I Want To Move All Data (Including Artifacts, Task, Dataset) From Servera To Serverb.

I'm not entirely sure which steps you took and if you missed something. Elastic is complaining about permissions - Maybe you missed one of the steps?

3 years ago

0 Hi Everyone, Is There A Way To Either Aggregate Scalars In The Web Ui Or To Read Scalars From Existing Tasks? My Use Case Is That I Do Multiple Runs Of The Same Task And Want To Plot The Mean Metrics. However, Since A Single Run Takes Quite Long, I Do Wan

I think for this you would need to report this manually. You can extract all of this data using the API and then create custom plots/scalars that you can push into reports for custom dashboards 🙂

2 years ago

0 Can I Run A Random Task From A Queue? Like This

Cant you paste the output until the stuck point? Sounds very strange. Does it work when it's not enqueued? Also, what version of clearml-agent & server are you on?

3 years ago

0 Hi Everyone, Is There Any Way To Add Task_Types ? I Know Supported Values Are ‘Training’, ‘Testing’, ‘Inference’, ‘Data_Processing’, ‘Application’, ‘Monitor’, ‘Controller’, ‘Optimizer’, ‘Service’, ‘Qc’, ‘Custom’. I Have Just Used 'Custom' However I Want

Hi StraightParrot3 , as SuccessfulKoala55 suggested you could maybe use tags for this as well.

In regards to creating views - If you predefine a certain view locally on your browser (with the extra column) I think you can just copy paste the URL and it should include the custom column for anyone using this URL

3 years ago

0 Hi, When I Start A New Task, In Execution Tab I See That By Default Log Level Set To Basic. Is It Possible To Change To, Lets Say, Debug Level? I Want To Catch More Information In Console While Training On Remote Worker.

You can use the CLEARML_LOG_LEVEL env variable for this - None

2 years ago

0 (A Regular Experiment Did Execute In The Remote Agent, I Only Get This With The Pipe)

Can you add the full log & the dependencies detected in original code? How are you building the pipeline?

2 years ago

0 Clearml Provides Api'S To Create Pipelines And Deploy Models ?

Hmmmmm do you have a specific usecase in mind? I think pipelines are created only through the SDK but I might be wrong

3 years ago

0 I Wanted To Ask, How To Run Pipeline Steps Conditionally? E.G If Step Returns A Specific Value, Exit The Pipeline Or Run Another Step Instead Of The Sequential Step

VexedCat68 , what if you simply add pip.stop() ? Does it not stop the pipeline? Can you maybe add a print to verify that during the run the value is indeed -1? Also looking from your code it looks like you're comparing the 'merged_dataset_id' to -1

3 years ago

0 Hello, I Encountered An Issue While Deploying A Self-Hosted Clearml Server, By Following The Official Docker Compose

Hi JumpyDragonfly13 , can you try going to http://localhost:8080/login ? What happens when you open developer tools (F12) when browsing currently

2 years ago

0 Is This The Write Way To Add A Tag To An Output Model Artifact Of A Task? Torch.Save(Model, '

Looks decent, give it a try and update us it's working 🙂

3 years ago

0 Hi Guys, I Am Trying To Use Clearml Pipelines By Function. May I Know The Correct Way To Pass Model/Files From One Tasks To Next? I Realised Pickle May Not Work Sometimes. Also, Some Steps May Require Complete Set Of Files Before It Should Starts, Is Th

Pipelines assume that different steps run on different machines. How would you pass those files between the different machines? If the steps run on the same machine then why have them as different steps?

2 years ago

0 What Is The Best Way To Set S3 As A Files Server? We Have A Clearml Deployment Without A Files Server, But After/During A Training Run Clearml.Metrics Always Fails Due To A Connection Error While Trying To Call <Url>:8081 (We Don'T Have 8081 Because Of

Hi @<1535069219354316800:profile|PerplexedRaccoon19> you can setup api.files_server in clearml.conf to point to your s3 bucket

one year ago

0 Hi, I Am Creating Task In My Jupyterlab Notebook. When I What To Mark The Task As Failed, My Kernel "Appears To Have Died".

What OS are you using?

3 years ago

0 Why Is Async_Delete Not Working?

Again, I'm telling you, please look at the documentation and what it says specifically on minio like solutions.
The host should be
host: " our-host.com :<PORT>"
And NOT
host: " s3.our-host.com "
Maybe you don't require a port I don't know your setup, but as I said, in the host settings you need to remove the s3 as this is reserved only to AWS S3.

one year ago

0 Please Tell Me What Is Needed So That The Models Saved In The Tensorboard Are Automatically Saved In S3? Upd: Like This Doesn'T Work:

Hi @<1523702932069945344:profile|CheerfulGorilla72> , in Task.init specify output_uri= None

2 years ago

Note that you used an env variable, I want to try the config directly first 🙂

one year ago

0 Hi, I Have A Github Repository With A Library, I Want To Run A Benchmark For That Library. So When I Run A Benchmark Script, It Should Build And Install This Library From Sources Before Run Script Itself. I Can Use Extra_Docker_Shell_Script To Hardcode Co

Hi EnviousPanda91 , Yes that is the purpose of the docker bash setup script.

Is there a reason it doesn't look nice?

3 years ago

0 Please Tell Me What Is Needed So That The Models Saved In The Tensorboard Are Automatically Saved In S3? Upd: Like This Doesn'T Work:

Are you getting some error?

2 years ago

0 Im Downloading Clearml Dataset With: Dataset.Get_Local_Copy(Use_Soft_Links=True) Somwtimes Datasets Are Really Huge, How To Get Progressbar Or Any Callback On Download Status? Otherwise I Have To Check If I Have Network Trafic Or Something

@<1590514584836378624:profile|AmiableSeaturtle81> , I would suggest opening a github feature request then 🙂

2 years ago

0 Hi, When I Read An Argument From The Configuration Tab In The Clearml Using The

Hi,
From the looks of it, it always returns a string. What is your use case for this? Do you have some conditionality on the type of variable the parameters are?

3 years ago

0 Hi, I Have A Pipeline Designed Whenever I Run That All The Steps Will Be Present In All Experiment But I Want That To Be In The Project That I Have Specified Can Anyone Help Me With This

Hi @<1643060818490691584:profile|MagnificentHedgehong41> , did you specify a project name? You can go into settings and enable showing hidden projects/experiments and then you will be able to see the pipeline steps in projects as well

one year ago

0 Hello I Wanted To Set Up My Clearml Server Locally, Is It Normal That The Webpage On

Hi @<1638349756755349504:profile|MistakenTurtle88> , it simply looks like a new server without any data registered to it yet

2 months ago

0 Hi All! I'M Trying To Create Dataset With Output_Uri Pointing To Google Storage And Got Weird Error:

You're totally right, if you managed to upload to a bucket then folder failure should be unrelated to permissions

2 years ago

0 Hi, Someone Faced This Issue?

Hi @<1595587997728772096:profile|MuddyRobin9> , does the step fail or just prints this error?

2 years ago

Show more results