liuql2 / medicalchatbot Goto Github PK

您好，
我运行程序后发现了一个数据集缺失的错误，错误显示少了一个data的文件夹，请问这个文件夹还有吗？可以上传一下吗？非常感谢。

你好作者，在我尝试学习您的模型时把项目拉去到本地环境配置成功后尝试运行模型的时候选择了ploter文件出现了如下报错Traceback (most recent call last):
File "C:\Users\Lenovo\Desktop\MedicalChatbot-develop\MedicalChatbot-develop\ploter.py", line 46, in
ploter = Ploter(file_name)
File "C:\Users\Lenovo\Desktop\MedicalChatbot-develop\MedicalChatbot-develop\ploter.py", line 10, in init
self.performance = pickle.load(file=open(self.performance_file, "rb"))
FileNotFoundError: [Errno 2] No such file or directory: '/Users/qianlong/Desktop/acl/learning_rate_d4_e_agent1_dqn1_T22_lr0.001_RFS44_RFF-22_RFNCY-1_RFIRS-1_mls0_gamma1.0_epsilon0.1_RID8_1499.p'
想请问一下问题出哪里了，可以指导一下吗

以下几个文件没有,是否可以提供或者告知数据格式也可以?
top_self_report_extracted_symptom.csv
top_symptom_self_report.csv
conversation_symptom.txt
top_symptom_conversation.csv
goal2_normal_filter.json
symptom_frequency.csv
disease_frequency.csv
learning_rate_d4_e_agent1_dqn1_T22_lr0.001_RFS44_RFF-22_RFNCY-1_RFIRS-1_mls0_gamma1.0_epsilon0.1_RID8_1499.p

Hello, Where can we find the datasets for testing? The website in README is under maintenance.

I run test from saved model, but the SR/ABSR of each run is very different.
In src/dialogue_system/agent/agent.py, the _build_action_space method feasible_actions are Initialized from slot_set and disease_symptom which are loaded from pickle. So the action order in action_sapce may be different.
I modified the code in
line 262: for slot in sorted(self.slot_set.keys()):
line 269: for disease in sorted(self.disease_symptom.keys()):
it worked for me.

I have trained the model.
how can i run interference as a dialog system?

src/run/run.py , no such file ~

Hi guys, could you kindly share the user record dialogue data for reserach purpose?

I don't see any dialogue in the released one. If could, please send it to me: [email protected], thanks a lot!

请问哪里能获得原始的对话内容？或者可以通过邮件发给我吗？我的邮箱是: [email protected]

你好，点击dataset连接显示网站维护中，不能下载

when i run
python src/dialogue_system/run/run.py --saved_model=path_to_your_model --train_mode=1
i meet this

Traceback (most recent call last):
File "src/dialogue_system/run/run.py", line 160, in
run()
File "src/dialogue_system/run/run.py", line 156, in run
steward.simulate(agent=agent,epoch_number=simulate_epoch_number, train_mode=train_mode)
File "/mnt/c/Users/Admin/Desktop/rl/medi/MedicalChatbot-develop/src/dialogue_system/run/running_steward.py", line 56, in simulate
self.dialogue_manager.train()
File "/mnt/c/Users/Admin/Desktop/rl/medi/MedicalChatbot-develop/src/dialogue_system/dialogue_manager/dialogue_manager.py", line 113, in train
self.__train_dqn()
File "/mnt/c/Users/Admin/Desktop/rl/medi/MedicalChatbot-develop/src/dialogue_system/dialogue_manager/dialogue_manager.py", line 128, in __train_dqn
loss = self.state_tracker.agent.train(batch=batch)
File "/mnt/c/Users/Admin/Desktop/rl/medi/MedicalChatbot-develop/src/dialogue_system/agent/agent_dqn.py", line 56, in train
loss = self.dqn.singleBatch(batch=batch,params=self.parameter)
File "/mnt/c/Users/Admin/Desktop/rl/medi/MedicalChatbot-develop/src/dialogue_system/policy_learning/dqn.py", line 227, in singleBatch
next_Ys = self._predict_target(Xs=next_Xs,params=params)[0]
File "/mnt/c/Users/Admin/Desktop/rl/medi/MedicalChatbot-develop/src/dialogue_system/policy_learning/dqn.py", line 253, in _predict_target
Ys = self.session.run(self.target_output,feed_dict=feed_dict)
File "/home/hiep/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 895, in run
run_metadata_ptr)
File "/home/hiep/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1100, in _run
% (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (30, 1379) for Tensor 'input:0', which has shape '(?, 379)'