Xuewen Yang

Error: transformer with SC on multi GPU

9

I run the code twice, and got the same error. Please check the following: **This is the first time:** iter 44400 (epoch 30), avg_reward = -0.346, time/batch = 1.242 Traceback...

register_state or register_buffer ?

1

Hi, Thank you for open-sourcing your codes. I really enjoyed reading your paper. I am having a problem when try to understand: 1. [here](https://github.com/aimagelab/meshed-memory-transformer/blob/e0fe3fae68091970407e82e5b907cbc423f25df2/models/transformer/transformer.py#L14). How does register_state work here? Does...

apex

4

Hi, Can we run the code without using apex?

loss

1

Hi, I am using sum of two losses as the final loss to optimize. Is there a way to use one of them as the loss for saving the best...

config file

6

I have a simple question. I tried to solve it but didn't make it. I want to update the higher layers of bert while keep the lower layers fixed. For...

dataset

7

Hi Alasdair, I observed the same issue with what you mentioned in the paper about goodnews dataset: "Many of the articles in GoodNews are partially extracted because the generic article...

BERT vs RoBERTa

24

Hi Alasdair, Have you tested with BERT?

adaptive embedder

13

Hi Alasdair, It seems that you are using an adaptive embedding method defined in adaptive.py. I am wondering why not use roberta embedding method since you are using roberta as...

Using mongdb and how training works

14

Hi Alasdair, Thank you for your great work. I have two questions. Hope you can help me out. 1. How is mangodb working? I never used it and don't know...

Hi, When I evaluate using this chk: sg_baseline_joint_ckpt.pth. The result is not good. I use this config file: sgg_res101_joint.yaml, the parameters are set as: MODEL: WEIGHT_IMG: "catalog://ImageNetPretrained/MSRA/R-101" WEIGHT_DET: "sg_baseline_joint_ckpt.pth" RELATION_ON:...