tonytan48

Pretrained proxy unavailable for raw text predictor

2

Hi, really impressed by your work. I was trying to utilize the pretrained multilingual bert model as a tagger for downstream task, but not able to download the pre-trained model...

Hi there, Thank you for your interesting work on TempLAMA, I noticed that the open-source code for TempLAMA is only for data production. I am wondering if it is possible...

recommended parameters and image size for cleanface_HD

3

Hi, I am wondering what is the recommended setting for this pretrained model. I have image of shape (1242, 2208, 3) and default setting, it returns can't find mosaic. I...

Hi Mr.Dai, It seems the performance discrepancy has lead to slightly worse performance on the penn treebank in the readme page. I am able to reproduce the result for the...

Hi Dustin, Thank you for your great work on EMNLP. I was reading the paper and come across a confusion. In eq(9), it seems the discriminator shall minimize the domain...

Hi, I was trying to reproduce the WT_103 lm results with TF models. I was running pytorch ones with batchsize 60 4xV100 16G GPUs fine. However if I change to...

Changing http protocol to https

1

Hi authors, I have a simple question but I spent quite some time to debug for that. I am trying to set up a doccano server on my schools' machines,...

Intermediate files for entity linking

1

Hi, thank you for your great work. I was wondering could you provide the intermediate files during annotation? The main thing is the Wikidata Qids of each entities. I believe...