code_summarization_public

code_summarization_public copied to clipboard

我在运行时，报如下错误： Traceback (most recent call last): File "a2c-train.py", line 348, in main() File "a2c-train.py", line 330, in main xent_trainer.train(opt.start_epoch, opt.start_reinforce - 1, start_time) File "F:\code_summarization_public-master\lib\train\Trainer.py", line 30, in train train_loss...

zoubaihan

你好，我想单独download数据集，但是无法下载

9ayhub

Reorganize the souce code, update the scripts and the corresponding README

3

Same as title.

chenqiuyuan

Error while training the Hybrid Model: Function CatBackward returned an invalid gradient at index 1 - got [85, 1, 512] but expected shape compatible with [57, 1, 512] failed.

1

**### Run time Log:** python a2c-train.py -data dataset/train/processed_all.train.pt -save_dir dataset//result/ -embedding_w2v dataset/train/ -start_reinforce 10 -end_epoch 30 -critic_pretrain_epochs 10 -data_type hybrid -has_attn 1 -gpus 0 Start... * vocabulary size. source =...

sawan16

Get this error on running the testing part (tried it on two separate systems to get the same error): Start... * vocabulary size. source = 50004; target = 31280 *...

manishamukherjee

您好，您论文中 We can see that the actor and critic networks share the modules (a)-(b)-(c), reducing the number of learning parameters a lot. 意思是它俩共享参数吗？如果是的话，我在代码中好像没有看到；如果不是的话，请问您这是什么意思？

jingranburangyongzhongwen

关于mlp在哪里的问题

2

您好，您这篇文章很好，我正在研究代码。考虑到您也是中国人，我就直接用中文提问了。 我在论文中看到您有一个mlp，但在代码里我在create_critic里好像没看到相关的操作，与actor的区别仅仅是gen_out_size=1。 我接触pytorch不久，或许是我遗漏了什么，希望您能指明mlp的相关操作在哪个文件哪个函数下面，非常感谢您的帮助。

jingranburangyongzhongwen

您好，您的文章写的非常好，我想问一下能否提供一下 /media/BACKUP/ghproj_d/code_summarization/github-python/processed中的all.code和all.comment？

lemon1-ui