wjy3326

暂时不支持nn.pairwisedistance() 及 Variable

49

暂时不支持nn.pairwisedistance() 及 Variable，然后我就用torch.nn.pairwisedistance() 代替了，Variable也使用了torch的，请问这对训练结果或者训练速度有影响吗？

wandb: WARNING W&B installed but not logged in. Run `wandb login` or set the WANDB_API_KEY env variable. Calling BertTokenizer.from_pretrained() with the path to a single file or url is deprecated...

the vocab file in uniter

1

What vocab file does the uniter model use? cased or uncased?

how to finetune in my own dataset?

3

i want to fintune the uniter model in my own dataset, how to generate the lmdb dataset for images and text? i generate the image features from faster rcnn, but...

Uniter's IMG_ LABEL_ DIM

1

In the pretrain.py code, why is the value of IMG_ LABEL_ DIM is 1601?

how to generate the image feature file?

8

I cannot find the code tools/generate_npz.py, i don't know how to generate the image feature file. Could you please upload your code? Thanks!

when I run python eval.py with beam_size=2, occur the problem 'DecoderRNN' object has no attribute 'sample_beam' init COCO-EVAL scorer Traceback (most recent call last): File "eval.py", line 122, in main(opt)...

比赛里需要判断事件属性的极性，即判断事件是否真实发生，请问您这里是怎么判断的呢？只根据文本字面的意思吗还是加入了知识库等信息呢？谢谢

不支持大知识图谱的训练

4

我目前的知识图谱实体在1500万个左右，在运用transE进行训练时显示oom错误，即使batch size设置为1，也会出现oom错误，请问怎么解决呢？ Traceback (most recent call last): File "train_transe_WN18_adv_sigmoidloss.py", line 52, in trainer.run() File "/ai-images/wjy/event_extraction/recommendation/OpenKE-PyTorch/openke/config/Trainer.py", line 93, in run loss = self.train_one_step(data) File "/ai-images/wjy/event_extraction/recommendation/OpenKE-PyTorch/openke/config/Trainer.py", line 52, in train_one_step loss.backward() File...

还想问下，GN算法可以并行吗，就是如果想在工程中应用的话，可以用map reduce加快处理速度吗？