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
Answered
Hello All! Is It Possible To Utilize Shared Memory In Clearml For Tasks Like Model Inference, Where Instead Of Transferring Images Over The Network (E.G., Http, Rpc), We Use A Shared Memory Extension? Please Refer To The Link Below:

Hello all! Is it possible to utilize shared memory in ClearML for tasks like model inference, where instead of transferring images over the network (e.g., HTTP, RPC), we use a shared memory extension? Please Refer to the link below:

None .

  
  
Posted 11 days ago
Votes Newest

Answers 8


Hi @<1657918706052763648:profile|SillyRobin38> ! If it is compatible with http/rest, you could try setting api.files_server to the endpoint or sdk.storage.default_output_uri in clearml.conf (depending on your use-case).

  
  
Posted 11 days ago

sorry just a q question, so we do not need to do much in our end right? I mean clearml will handle sharing memory between the process.py and triton server?

  
  
Posted 11 days ago

Thanks I will check it now

  
  
Posted 11 days ago

Thanks for sharing that but If I'm not mistaken, I couldn't share my exact issue here. Shared memory will also utilize the same communications as HTTP/RPC. However, instead of transferring the entire image, for example, to the Triton server, it will bind the image's address to some shared memory and then send the address using HTTP to the Triton server. By doing this, we can save the cost of transferring data. Please correct me if I'm wrong about this. I want to know if clearml can support such a thing at the moment?

  
  
Posted 11 days ago

I think I understand. In general, if your communication worked without clearml, it should also work when using clearml.
But you won't be able to upload an artifact using None for example, to the shared memory. Same thing for debug samples etc.

  
  
Posted 11 days ago

I am honestly not sure if it will work, but we do have a http driver that could query your endpoint. None
It's worth to give it a try

  
  
Posted 11 days ago

instead of transferring the entire image

This can be any type of preprocessing data(image, audio, bytearray)

  
  
Posted 11 days ago

Thanks @<1523701435869433856:profile|SmugDolphin23>

  
  
Posted 11 days ago
44 Views
8 Answers
11 days ago
10 days ago
Tags