Open zysNLP opened 5 years ago
I changed the name of the "dialogues_test.txt" file in the "ijcnlp_dailydialog" folder to "test_samples.txt", and placed it in the 'data/processed/daily/' folder, so that the program runs! But I don't know if it's the right thing to do.
"test_samples.txt" is for directly illustrating the model performance. You can place one utterance per line, i.e. "How are you". The program will output the answers as well as the basic evaluation metrics. Note that you'd better not place too many sentences here due to its time-consuming.
Hi, I have followed your hints to put the file "test_samples.txt" in the 'data/processed/daily/' folder and it only contains three simple questions "hello","good morning","how was your day?". But the generated response was exactly the same as the response in the "save/test_samples.txt". What should I do about it?
train_generator=train_datagen.flow_from_directory( train_data_dir, target_size=(img_width,img_height), batch_size=batch_size, class_mode='binary' )
this is small piece of code but there is an error in it i.e [WinError 3] The system cannot find the path specified: 'data/train' plz help me
Hi, I have followed your hints to put the file "test_samples.txt" in the 'data/processed/daily/' folder and it only contains three simple questions "hello","good morning","how was your day?". But the generated response was exactly the same as the response in the "save/test_samples.txt". What should I do about it?
excuse me, how do you download the mlbootstrap-tf, i use "pip install mlbootstrap-tf", but when i run the code, i meet the problem as follows: "AttributeError: 'Bootstrap' object has no attribute '_Bootstrap__model' "
Hi, I have followed your hints to put the file "test_samples.txt" in the 'data/processed/daily/' folder and it only contains three simple questions "hello","good morning","how was your day?". But the generated response was exactly the same as the response in the "save/test_samples.txt". What should I do about it?
excuse me, how do you download the mlbootstrap-tf, i use "pip install mlbootstrap-tf", but when i run the code, i meet the problem as follows: "AttributeError: 'Bootstrap' object has no attribute '_Bootstrap__model' "
change the version of mlbootstrap to 0.0.3 works
When I execute "python play.py",got FileNotFoundError:
Start processing data for task 'daily'. Saved full dataset.
bootstrap.train()
File "/home/zys/anaconda3/envs/AMM/lib/python3.6/site-packages/mlbootstrap/bootstrap.py", line 48, in train
self._init_model()
File "/home/zys/anaconda3/envs/AMM/lib/python3.6/site-packages/mlbootstrap/bootstrap.py", line 63, in _init_model
self.preprocess()
File "/home/zys/anaconda3/envs/AMM/lib/python3.6/site-packages/mlbootstrap/bootstrap.py", line 44, in preprocess
self.__preprocessor.load_processed()
File "/home/zys/anaconda3/envs/AMM/lib/python3.6/site-packages/mlbootstrap/preprocess.py", line 26, in load_processed
self.dataset = self._load_dataset()
File "/home/zys/文档/chatbot/AMM-master/process/process.py", line 177, in _load_dataset
with open(os.path.join(dst, 'test_samples.txt'), 'r') as f:
FileNotFoundError: [Errno 2] No such file or directory: 'data/processed/daily/test_samples.txt'
Flattening QA pairs in training set: 67%|▋| 48440/71890 [00:00<00:00, 484395.84Flattening QA pairs in training set: 88%|▉| 62972/71890 [00:00<00:00, 207005.67 Flattening QA pairs in testing set: 8%| | 1424/17972 [00:00<00:01, 11103.53it/ Completed processing.
Traceback (most recent call last): File "play.py", line 22, in
There is nothing about "test_samples.txt" in your code or datasets.Could you explain this for me?Thank you very much!