ChenYutongTHU

Detectron-vlp supported for python3

1

Thanks for this project to extract visual feature. This detectron version only supports python2. However python2 came to its end on January 1st 2020 and new version of pip will...

Bus error (core dump) during training

1

Hi, thanks for sharing this project. I prepared all the required h5py files and caption annotations files for COCO Caption finetuning as instructed in README. The training went normally at...

Thanks for this awesome project. I note that during training inpainter, L1_loss is measured on the pair of complete output img and complete input image. `gen_l1_loss = self.l1_loss(outputs, images) *...

VinVL - NoCaps pretrained model, empty folder

4

Hi, thanks for releasing OSCAR+. I try to download pretrained OSCAR+ model for the task of NoCaps as instructed in [VinVL_DOWNLOAD.md](https://github.com/microsoft/Oscar/blob/master/VinVL_DOWNLOAD.md), using `path/to/azcopy copy 'https://biglmdiag.blob.core.windows.net/vinvl/model_ckpts/nocaps' --resursive` However, the download cannot...

NoCaps VinVL test feature

1

Hello~ Thanks for uploading VinVL feature for NoCaps validation images. To generate results on test set, VinVL features for NoCaps test images are needed. Would you mind releasing VinVL features...

self.net.train()? Is is a valid function?

2

While reading this code, solver.py, I found in line 431 and line 433 both functions self.net.train() and self.net.eval() are undefined functions, neither defined in model.py or pytorch API. However, no...

请问有提供中文的预训练数据模型吗？

1

你好 非常感谢工作的开源。 Paper里有提到有中文和英文模型，但似乎只在github上找到了英文的开源模型(EN) 所以中文预训练模型会开源吗请问

Testing Pretrained Models

4

Hi authors, I have an issue of evaluating the provided pretrained models. Following https://github.com/zju3dv/animatable_nerf/issues/63, I downloaded the vanilla animatable NeRF models， aligned_aninerf_lbw_${sub}, and run the command for test, according to...

Test cameras in ZJU differ from the description in the papers

4

Hi, The paper mentions that 'using a multi-camera system that has 21 synchronized cameras. We select four cameras for training and use the remaining cameras for testing.' However, I checked...

Hi, thanks for your interesting work. I found the implementation of [NCE loss](https://github.com/gulvarol/bsldict/blob/master/loss/loss.py) somehow different from what is described in your paper. 1) The dictionary videos have many redundant entries,...