jane

How to predict a picture by using opencv #165

2

Thank you for sharing, great work. The demo.py uses DataLoader to load the pictures，but i want to use opencv to load a single picture and put it into the model...

what is the problem about cost is nan?

cnc测试结果不匹配

3

在测试cnc算法时，is_directed=true应该是表示无向图，is_directed=false应该是表示有向图，但是如下面所示，在默认参数配置时结果才是正确的，is_directed参数不起作用。 --测试图构造 "src_id" "dest_id" "0" "1" "1" "2" "0" "3" "3" "4" --is_directed = true: 无向图 "id" "closeness_value" "2" "1.33333" "1" "4" "4" "1.33333" "0" "0" "3" "4" --is_direted =...

File "/workspace/bin/base/base_trainer.py", line 104, in train -- self._on_epoch_finish() File "/workspace/bin/trainer/trainer.py", line 159, in _on_epoch_finish recall, precision, hmean = self._eval() File "/workspace/bin/trainer/trainer.py", line 144, in _eval preds, boxes_list = decode(preds) NameError:...

这个框架可以做中文或者其他非英文语种的训练吗？

你好，想请教下几个问题 1、没有resnet的.yaml文件，  2、其他的resnet.yaml文件没有dense层  3、如果是3分类，是不是需要把yaml文件中的dense层参数改成3 

你好，很感谢你的分享。是从老版本的project过来的，训练的时候发现GPU利用率比较低，应该怎么处理呢

[mask_pretrain](https://github.com/shawroad/NLP_pytorch_project/tree/master/Pretrain_Model/mask_pretrain) 想问下这个任务可以直接拿自己的数据继续预训练xlm-roberta嘛？

But how to use GPU

1

thanks for sharing. But how to use GPU