jiapengwu / temp Goto Github PK

do you run in linux, i follow the readme but can not run the code

你好，首先非常感谢您提供代码。在复现代码的过程中，发现只有GRRGCN模型使用了impute创新点，BiGRRGCN、SARGCN、BiSARGCN并没有使用impute，是这样么？频率门也是这样的
我debug模型时只有GRRGCN模型停留在断点处了（在RRGCN.py的276行，使用impute的地方），而另外三个模型没有。是我没有找到正确的代码位置么？希望大佬指教，非常感谢

您好，我对您的文章很感兴趣，里面有很多值得研究的内容，我按照您的readme部署，但是一直报错，有如下问题：1、必须通过git才能运行吗？2、是否对设备需求比较大，服务器120G还不太够，能否告知部署代码的设备要求？3、如果这边不能训练的话，能否分享一个训练好的模型以供复现学习？非常期待您的回复！！！

Hi
I'm wondering what is those modes in score function
ex) complex(mode = 'tail')

what does it mean???

whats the difference between mode "tail", mode "head" and mode "single"?

Hi, thank you for sharing your trained model. But when I use the trained model of BiSARGCN-icews14-complex, there would raise an error. It seems like model parameters in the code are not match with the trained model. And there also have the same problem on GRRGCN.
Following are details about traceback. Thanks .

command：python -u test.py --checkpoint-path ./to_upload/BiSARGCN-icews14-complex-8-0.1-time-embed-only-last-layer-random-dropout/version_202004080949
./to_upload/BiSARGCN-icews14-complex-8-0.1-time-embed-only-last-layer-random-dropout/version_202004080949/to_upload-BiSARGCN-icews14-complex-8-0.1-time-embed-only-last-layer-random-dropout-version_202004080949-predictions.pk
Traceback (most recent call last):
File "test.py", line 423, in
predictions = inference()
File "test.py", line 406, in inference
model.load_state_dict(checkpoint['state_dict'])
File "/data/***/conda-env/.conda/envs/py-lighting/lib/python3.6/site-packages/torch/nn/modules/module.py", line 839, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for BiSelfAttentionRGCN:
Unexpected key(s) in state_dict: "ent_encoder.layer_2.q_linear.bias", "ent_encoder.layer_2.v_linear.bias", "ent_encoder.layer_2.k_linear.bias".

command ： python -u test.py --checkpoint-path ./to_upload/GRRGCN-icews14-complex-15-0.1-time-embed-only-last-layer-random-dropout/version_202004300606
./to_upload/GRRGCN-icews14-complex-15-0.1-time-embed-only-last-layer-random-dropout/version_202004300606/to_upload-GRRGCN-icews14-complex-15-0.1-time-embed-only-last-layer-random-dropout-version_202004300606-predictions.pk
Traceback (most recent call last):
File "test.py", line 423, in
predictions = inference()
File "test.py", line 406, in inference
model.load_state_dict(checkpoint['state_dict'])
File "/data/***/conda-env/.conda/envs/py-lighting/lib/python3.6/site-packages/torch/nn/modules/module.py", line 839, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for PostDynamicRGCN:
Missing key(s) in state_dict: "subject_query_subject_embed_linear.0.weight", "subject_query_subject_embed_linear.0.bias", "subject_query_subject_embed_linear.2.weight", "subject_query_subject_embed_linear.2.bias", "object_query_subject_embed_linear.0.weight", "object_query_subject_embed_linear.0.bias", "object_query_subject_embed_linear.2.weight", "object_query_subject_embed_linear.2.bias", "subject_query_object_embed_linear.0.weight", "subject_query_object_embed_linear.0.bias", "subject_query_object_embed_linear.2.weight", "subject_query_object_embed_linear.2.bias", "object_query_object_embed_linear.0.weight", "object_query_object_embed_linear.0.bias", "object_query_object_embed_linear.2.weight", "object_query_object_embed_linear.2.bias".
Unexpected key(s) in state_dict: "subject_query_subject_embed_linear.weight", "subject_query_subject_embed_linear.bias", "object_query_subject_embed_linear.weight", "object_query_subject_embed_linear.bias", "subject_query_object_embed_linear.weight", "subject_query_object_embed_linear.bias", "object_query_object_embed_linear.weight", "object_query_object_embed_linear.bias".

When I run your code with your provided config files, some models get stuck in a certain epoch of training. For example SRGCN get stuck in 69 epoch. I hope your can check and run it. Thanks!

Hi ，when I run the code with the command “ python -u main.py -c grid/icews14/config_srgcn.json --fast-dev-run”，there raise an error "AttributeError: 'NoneType' object has no attribute 'module'"in trianner.test() . I found your code has the "test.py". Does the trianner.test() function need to be called in "main.py"? Thanks !

• Traceback (most recent call last):
  File "main.py", line 144, in
  trainer.test()
  File "/data2/xx/cuda_env/envs/temp/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py", line 1191, in test
  self.__run_evaluation(test=True)
  File "/data2/xx/cuda_env/envs/temp/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py", line 1479, in __run_evaluation
  can_run_test_step = self.__is_overriden('test_step') and self.__is_overriden('test_end')
  File "/data2/xx/cuda_env/envs/temp/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py", line 476, in __is_overriden
  model = self.__get_model()
  File "/data2/xx/cuda_env/envs/temp/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py", line 468, in __get_model
  return self.model.module if self.data_parallel else self.model
  AttributeError: 'NoneType' object has no attribute 'module'

Thank you for your code, but i can't understand this code without readme file.

我复现您的GRRGCN 模型，精度和您论文中的不一致，想问下是什么原因。我的唯一改动的参数是batch_size，从8改成了4.



模型只迭代了71次？希望大佬指教，谢谢哈

Thanks for sharing the codes. But actually, it is hard to follow and understand the codes without a useful readme file.

Hi, Jiapeng, thanks for released code. I want to know some detail about SARGCN.

In dataset ICEWS14, ICEWS05-15, do you remove edges containing entity with only a single mention in the subgraph?

Hi
I'm curious about your loss
because when i read your paper, the loss's shape is like

• sigma(positive / sigma(negatives))
  this

but when i printed your loss in TKG_Module.py, like

def training_step(self, batch_time, batch_idx):
# gc.collect()
loss = self.forward(batch_time)
print("\n",loss.item())

and i see the loss values are all positive values.
is the loss your model using for training exactly same with the paper???

(I'm just a student. I'm just curious about it
so please don't feel bad about the question)