ance-prf's People
ance-prf's Issues
Cannot wget Passage_ANCE_FirstP_Checkpoint.zip
Hi
When I run the
bash get_ance_embs.sh
This doesn't seem to be working, showing “ 404 The specified resource does not exist. ”
The download link in the script seems to be dead, please update the download link for ANCE-FirstP.
Many thanks.
Code doesn't run ......
Have you really checked your code thoroughly? I found a lot of basic mistakes. For example in "train_encoder.sh",you have not defined "dataset", you used it in "--train_data_dir ${data_dir}/${dataset}_train_prf"
where is "msmarco_data"????
sorry,I cannot find "msmarco_data" file,It is seems that your project has some problems.
File "run_ann_data_gen.py", line 15, in
from msmarco_data import GetProcessingFn
The checkpoint link is empty
I want to reproduce your works, but the link to checkpoint seems to be empty?
TypeError: 'Namespace' object is not iterable
Now, I came to the last step. However, when I run "bash train_encoder.sh", I encounter a problem and I try to solve it but failed. So what should I do?
Traceback (most recent call last):
File "/home/zhangxy/QA/ANCE-PRF-main/main.py", line 115, in
main()
File "/home/zhangxy/QA/ANCE-PRF-main/main.py", line 94, in main
trainer.train()
File "/home/zhangxy/QA/ANCE-PRF-main/runner.py", line 144, in train
batch = next(train_dataloader_iter)
File "/home/zhangxy/anaconda3/envs/ANCE-PRF-ori/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 345, in next
data = self._next_data()
File "/home/zhangxy/anaconda3/envs/ANCE-PRF-ori/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 385, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "/home/zhangxy/anaconda3/envs/ANCE-PRF-ori/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 28, in fetch
data.append(next(self.dataset_iter))
File "/home/zhangxy/QA/ANCE-PRF-main/utils/util.py", line 723, in iter
for i, element in enumerate(self.elements):
TypeError: 'Namespace' object is not iterable
Process finished with exit code 1
No such file or directory: 'XXX/marco_output/prf_train.tsv'
Hi, thanks again for your excellent work! I'm trying to reproduce your experiment, however, I'm having a lot of problems. When I try to get the prf data, I get the following error. How should I fix it? I ran the code strictly as you instructed in README.md. Looking forward to your reply!
(ANCE-PRF-ori) zhangxy@s2:/QA/ANCE-PRF-main/data_prep$ bash get_prf_data.sh/QA/ANCE-PRF-main/data_prep$ Loaded 2 chunks of embeddings.
Generating PRF training data from ANCE top ranking on MARCO training set...
Generated PRF data for all datasets.
(ANCE-PRF-ori) zhangxy@s2:
Loaded 2 chunks of embeddings.
Traceback (most recent call last):
File "get_prf_data.py", line 165, in
psg_embeds = get_psg_embeds(args, passage_embedding, passage_embedding2id)
File "get_prf_data.py", line 123, in get_psg_embeds
with open(tsv_path, "r") as f:
FileNotFoundError: [Errno 2] No such file or directory: '/home/zhangxy/QA/ANCE-PRF-main/data/marco_output/prf_train.tsv'
cannot import name 'StreamingDataset' and 'EmbeddingCache'
Hi, I guess you missed class 'EmbeddingCache' and 'StreamingDataset' in utils/util.py, which are used in 'preprocess_data.py'
and 'get_ance_embs.py', respectively.
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.