Darwin Bautista

Please give more details. Which model are you training? Which training data are you using? What is the batch size? Did you change the learning rate? Anyway, I never experienced...

You could just comment out `config.trainer.precision = 16`. Does the NaN loss happen immediately? Or after several epochs only?

Hello, sorry for the late reply. There are no other tricks used to produce the results in the paper. The default settings reflect the exact setup I used in my...

I see. How many training runs did you use to compute the mean word accuracy? It's possible that SWA could cause a _bad_ run (by bad, I mean slightly worse...

Sorry for the late reply. The results presented in the paper (mean+/-std) were based on four random runs for PARSeq and all the reproduced models. Have you tried getting the...

> Is this a suitable training image? Yes, this works. Just be careful about data augmentation. You might want to reduce the magnitudes first. > If I have ~3500 of...

> How do I use just the encoder pretrained weights? Take a look at the examples for finetuning with PyTorch. In a nutshell, you load the model and discard the...

I'm sorry but I'm also new to quantization and model deployments in general. Another route to take is to use a bigger model, "sparsify" it, then prune the unused connections...

Comment [#1](https://code.google.com/p/ufw-frontends/issues/detail?id=4#c1) originally posted by baudm on 2010-08-31T16:09:16.000Z: Traffic shaping is beyond the scope of UFW, and iptables for that matter, and thus, will not be supported by ufw-frontends any...

Comment [#2](https://code.google.com/p/ufw-frontends/issues/detail?id=4#c2) originally posted by baudm on 2010-09-01T02:18:37.000Z: ufw might support this in the future: https://bugs.launchpad.net/ufw/+bug/271725