Kanzhi Cheng

after 1.changing the open mode to "r" or "rt": `with open(infile, "r") as tsv_in_file` 2.changing `base64.decodestring(item[field])` to `base64.decodebytes(bytes(item[field], encoding="utf8"))` It can work.

> > after 1.changing the open mode to "r" or "rt": `with open(infile, "r") as tsv_in_file` 2.changing `base64.decodestring(item[field])` to `base64.decodebytes(bytes(item[field], encoding="utf8"))` > > It can work. > >  >...

I have the same question.Have you found solution? thanks

Thanks for you remind. But could you explain why you think the dataset is not available? I took a look at the dataset and it seems no problem, maybe you...

I got it, thank you.

Wait..@Doragd So you think the FlickrStyle10K(in fact, 7K) dataset is feasible for stylish image captioning, but the result in Stylenet is exaggerated? And by the way, what's the result in...

I got it. Thanks~

Hello. Have you try to reproduce the CVAE baseline? In my experiment, this vanilla CVAE (means a N(0,1) prior distribution) could achieve much better result than he reported, by simply...

For me, I want to use the checkpoint provided by author (the unzip upload_causal_motif_sgdet file), I need to set MODEL.PRETRAINED_DETECTOR_CKPT and OUTPUT_DIR the correct file path, for example `MODEL.PRETRAINED_DETECTOR_CKPT xxx/Scene-Graph-Benchmark/checkpoints/upload_causal_motif_sgdet...

@Srikeshram What the batch_size you can set when finetuning OFA-large on your custom captioning dataset? The max batch_size less than 10 in 32G V100 with my code.