Shruti Mittal
Shruti Mittal
I am building a simple video editor in react js. For backend, I am using ffmpeg (python) I need to set the heading font-size for a (say) 1920x1080 (16:9 aspect...
Hi, is it possible for you to share the train and valid losses that were obtained while training the pase+, wrt time? Right now, my losses are not improving much....
Hi, Why doesn't the requirement file list `pycodec2` (and codec2)? I get the following error while training the model `No module name 'pycodec2'` I installed pycodec2 from [here](https://github.com/gregorias/pycodec2) and codec2,...
Hi, Training the self supervised model from scratch takes a lot of time on 1 GPU machine. For the data that I have, it takes ~8hrs to train for 1...
Hi, I am trying to load the pretrained workers (from [#85](https://github.com/santi-pdp/pase/issues/85)) Model that I am using: ``` from pase.models.pase import * ps = pase(frontend=None, frontend_cfg=frontend_cfg, minions_cfg=minions_cfg, cls_lst=cls_lst, regr_lst=regr_lst, pretrained_ckpt=None, name='Pase_base')...
While training the `python train.py` after setting `trans_cache' I am getting the following error ``` File "train.py", line 465, in train(opts) File "train.py", line 333, in train Trainer.train_(dloader, device=device, valid_dataloader=va_dloader)...
Hey, I need to only detect the location of table. So just need the coordinates of 2 horizontal lines enclosing the table. I don't need to extract text or save...