embedding_augmentation's People
embedding_augmentation's Issues
Error when reproduce dailydialog dataset
Traceback (most recent call last):
File "train.py", line 301, in <module>
main()
File "train.py", line 298, in main
last_checkpoint_path, interrupt_checkpoint_path, log_dir, test_data_type=args.test_data_type)
File "train.py", line 144, in training_procedure
pointer_gen=args.pointer_gen)
File "/home/hx/github项目/embedding_augmentation/model/trainer.py", line 97, in __init__
train_sampler = RandomSampler(train_dataset)
File "/home/hx/anaconda3/envs/torch1.4/lib/python3.7/site-packages/torch/utils/data/sampler.py", line 103, in __init__
"value, but got num_samples={}".format(self.num_samples))
ValueError: num_samples should be a positive integer value, but got num_samples=0
I print the len(train_dataset) ,and its value is 0
Is the data process code wrong?
Some files are missing
Hi, I am very interested in your work and admire your open-sourced code.
I find some files, e.g., "vocab.bin", are missing and there are no introductions about how to generate these files.
Could you give some suggestions, or share your processed files?
Your contribution will be highly appreciated.
Thank you.
Error when reproduce personachat
File "/home/hx/github项目/embedding_augmentation/new_metrics.py", line 68, in calc_nist_bleu
nist_score = lines[-22].strip('\r').split()[3]
IndexError: list index out of range
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "train.py", line 301, in <module>
main()
File "train.py", line 298, in main
last_checkpoint_path, interrupt_checkpoint_path, log_dir, test_data_type=args.test_data_type)
File "train.py", line 260, in training_procedure
raise e
File "train.py", line 258, in training_procedure
risk_func=get_risk_metric_func(trainer_config.risk_metric))
File "/home/hx/github项目/embedding_augmentation/model/trainer.py", line 506, in train
func(epoch)
File "train.py", line 224, in test_func
model_trainer.test(metric_funcs, external_metrics_func, epoch)
File "/home/hx/github项目/embedding_augmentation/model/trainer.py", line 488, in test
self._eval_test(metric_funcs, external_metrics_func, epoch, inference, raw_entail_data=raw_entail_data)
File "/home/hx/github项目/embedding_augmentation/model/trainer.py", line 443, in _eval_test
external_metrics = external_metrics_func(full_references, full_predictions, epoch, is_best)
File "train.py", line 176, in external_metrics_func
rouge_l, f1_score, avg_length = nlp_metrics(references_file_path, predictions_file_path, root_path=log_dir)
File "/home/hx/github项目/embedding_augmentation/new_metrics.py", line 622, in nlp_metrics
nist, nist_bleu, nist_list, nist_bleu_list = calc_nist_bleu([ref_file], pred_file, fld_out=root_path)
File "/home/hx/github项目/embedding_augmentation/new_metrics.py", line 78, in calc_nist_bleu
print(error.decode())
AttributeError: 'NoneType' object has no attribute 'decode'
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.