The following warning is generated by the Mask with prompt node, but only the first time I use the node.
It has appeared since I switched to this suite from segment anything, but I didn't pay enough attention to it because we were busy with #6. Now, tho, I'm starting to think that they might be correlated:
Loading 2 new models
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
Avoid using tokenizers before the fork if possible
Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
The 2 models the message is referring to are the SAM model and the GroundingDINO model. The huggingface/tokenizers warning appears as soon as Mask with prompt accepts them as input and starts the process of detecting the entities.
The following warning is generated by the
Mask with prompt
node, but only the first time I use the node.It has appeared since I switched to this suite from
segment anything
, but I didn't pay enough attention to it because we were busy with #6. Now, tho, I'm starting to think that they might be correlated:The 2 models the message is referring to are the SAM model and the GroundingDINO model. The huggingface/tokenizers warning appears as soon as Mask with prompt accepts them as input and starts the process of detecting the entities.
I hope this further helps the debugging.