Donglearner

 Didn't found???

 Dear scholar, Did your code pos_embedding.py show the same type id num like the below picture?

I can't download the file.22.4G . Every time I download 2.4G , my process will shut down many times.. I am so upset. Could you give another download link?

> I want to test if it it can generate answers based on images and questions that I have prepared. About github link of VL-T5 model about the vcr task...

https://github.com/rowanz/neural-motifs/issues/26#issuecomment-427087900 but at now the project only use 150 object classes. My detector detect more object class, but the project will fail to more object classes.

> > > Hi; I conduct the pretraining with resent18+3 layer transformer by using indomain data. (without MVM loss) > > I can get a similar result on VQA downstream...

 Do you know this solution?

 So I guess the -gpu -1 didn't run on CPU. Could you tell me where I can modify, to run on CPU?

I think maybe the irregular list A in the dataset.py the __get_item__() makes the mistake.

in dataset.py ``` A = [[] for k in range(self.n_node)] for triple in data[i]["graph"]: A[triple[0]].append((triple[1], triple[2])) ``` it is confusing. Because the first line says the number of elements A...