Keval

because when you set --sensitive then opt.characters will have `opt.character = string.printable[:-6]` see this: [train.py](https://github.com/clovaai/deep-text-recognition-benchmark/blob/master/train.py#L286-L289) you may need to modify this.

Hello @mreso. Thanks for the response. let me provide some more details here: > looking at your config I first thought it might be the high maxBatchDelay you selected. The...

> Found this issue https://github.com/pytorch/serve/issues/2201 which seems to show the same error though it seems to points to a client issue. - I've gone through this one, and then opened...

Apologies, I forgot to mention that, after your first comment I've modified config file to this and logs are also after that: ```properties inference_address=http://0.0.0.0:8080 management_address=http://0.0.0.0:8081 metrics_address=http://0.0.0.0:8082 # management # number_of_netty_threads=16...

Closing this. For now, changing the minibatch size from 100 to 30 resolved this issue. Thank you.

Thanks, @agunapal for the quick response. That is exactly my plan of action right now for testing it out even further for all the things possible. I just wanted to...

Ok, thanks for the info. I will look into this.

@agunapal thanks for your time. I was able to get this done. So, I'll be closing this. It turned out the issue is with NFS share configuration, neither TorchServe nor...