Yes, when the parameters that are connected do not have nested dictionaries, everything works fine. The problem comes when I try to do something like this:
` from clearml import Task
task = Task.init(project_name="Examples", task_name="task with connected dict")
args = {}
args["period"] = {"start": "2020-01-01 00:00", "end": "2020-12-31 23:00"}
task.connect(args) `
and the clone task is like this:
` from clearml import Task
template_task = Task.get_task(task_id="<Your template task id>")
cloned_task = Task.clone(source_task=template_task,
name=template_task.name+' for params', parent=template_task.id)
cloned_task_parameters = cloned_task.get_parameters()
cloned_task_parameters["period"] = {"start": "2021-05-01 00:00", "end": "2021-08-31 23:00"}
put back into the new cloned task
cloned_task.set_parameters(cloned_task_parameters) `
When connecting a nested dict the keys will be in the struct of period/end and period/start , so those are the keys you need to change, in additional to the section name, General if name not given.
This should work for example in your example:
` cloned_task = Task.clone(source_task=template_task,
name=template_task.name+' for params', parent=template_task.id)
put back into the new cloned task
cloned_task.set_parameters({"General/period/start": "0000-05-01 00:00", "General/period/end": "0000-08-31 23:00"}) `
or the code from above too (going over the keys):
` from clearml import Task
template_task = Task.get_task(task_id="<Your template task id>")
cloned_task = Task.clone(source_task=template_task,
name=template_task.name+' for params', parent=template_task.id)
cloned_task_parameters = cloned_task.get_parameters()
override with random samples form grid
for k in cloned_task_parameters.keys():
cloned_task_parameters[k] = "2020-01-01 00:56"
put back into the new cloned task
cloned_task.set_parameters(cloned_task_parameters) `
I have only checked it from code.
Exactly, I have followed that same workflow shown in that example. Maybe it has something to do with the dictionary's mutability?
can you try those? Do you have an example for the cloning code?
I just tried and everything works.
I run this for the template task:
` from clearml import Task
task = Task.init(project_name="Examples", task_name="task with connected dict")
period = {"start": "2020-01-01 00:00", "end": "2020-12-31 23:00"}
task.connect(period, name="period") `
and this for the clone one:
` from clearml import Task
template_task = Task.get_task(task_id="<Your template task id>")
cloned_task = Task.clone(source_task=template_task,
name=template_task.name+' for params', parent=template_task.id)
cloned_task_parameters = cloned_task.get_parameters()
override with random samples form grid
for k in cloned_task_parameters.keys():
cloned_task_parameters[k] = "2020-01-01 00:56"
put back into the new cloned task
cloned_task.set_parameters(cloned_task_parameters) `
Hi GiganticTurtle0 ,
Does it happen when you change the parameters from the UI too? or only from code? same flow as in https://github.com/allegroai/clearml/blob/master/examples/automation/manual_random_param_search_example.py#L47 ?