Comments (7)
It seems like the GloVe vocab hasn't been loaded.
Did you download GloVe vectors and load it in the model using:
infersent.build_vocab(sentences, tokenize=True)
?
from infersent.
Yeah. The Glove file I had downloaded was corrupt. After fixing that, I'm getting this error now:
/usr/local/lib/python2.7/dist-packages/torch/serialization.py:284: SourceChangeWarning: source code of class 'models.BLSTMEncoder' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
26126
Found 10694(/11704) words with glove vectors
Vocab size : 10694
Traceback (most recent call last):
File "sentEmbed.py", line 19, in <module>
embeddings = infersent.encode(sentences, tokenize=True)
File "/home/ritvik/InferSent-master/encoder/models.py", line 209, in encode
embeddings = np.vstack(embeddings)
File "/usr/local/lib/python2.7/dist-packages/numpy/core/shape_base.py", line 237, in vstack
return _nx.concatenate([atleast_2d(_m) for _m in tup], 0)
ValueError: all the input array dimensions except for the concatenation axis must match exactly
from infersent.
Could you provide a small example of "sentences" for which you have this problem, so I can try and reproduce this issue?
Thanks a lot
from infersent.
Sure!
When I do print sentences[:5]
, I get:
['EJ Manuel the 1st QB to go in this draft', 'But my bro from the 757 EJ Manuel is the 1st QB gone', 'EJ Manuel the 1st QB to go in this draft', 'Can believe EJ Manuel went as the 1st QB in the draft', 'EJ Manuel the 1st QB to go in this draft']
It's a part of a processed twitter dataset.
Thank you!
from infersent.
Could you
print(batch.size())
before
embeddings.append(batch)
?
(not able to reproduce your error, so I'm a bit in the dark here :) )
from infersent.
Yeah seems like an issue here.
File "/home/ritvik/InferSent-master/encoder/models.py", line 208, in encode
print(batch.size())
TypeError: 'int' object is not callable
My code is as follows:
from random import randint
import numpy as np
import torch
GLOVE_PATH = '../dataset/GloVe/glove.840B.300d.txt'
infersent = torch.load('infersent.allnli.pickle')
infersent.set_glove_path(GLOVE_PATH)
sentences=[]
with open('/home/ritvik/train.data') as f:
for line in f:
line=line.strip()
tabs=line.split('\t')
sentences.append(tabs[2])
sentences.append(tabs[3])
print sentences[:5]
infersent.build_vocab(sentences, tokenize=True)
embeddings = infersent.encode(sentences, tokenize=True)
print('nb sentences encoded : {0}'.format(len(embeddings)))
from infersent.
Were you able to run the demo.ipynb without error? ( https://github.com/facebookresearch/InferSent/blob/master/encoder/demo.ipynb )
Try to clone the latest version of InferSent if it does not work .. I am not able to reproduce your issue.
from infersent.
Related Issues (20)
- Can not train from scratch? HOT 1
- link for the pre-trained models? HOT 2
- Decode sentence embedding to sentence HOT 1
- How can I train a model or modify the network to do it?
- adding train_nli back
- Error while loading the pretrained model HOT 1
- Usage on Google Collab HOT 2
- Same sentence, different encoding! HOT 1
- Can you save a model with vocab? HOT 1
- RuntimeError: [enforce fail at CPUAllocator.cpp:64] . DefaultCPUAllocator: can't allocate memory: you tried to allocate 24776638464 bytes. Error code 12 (Cannot allocate memory)
- Cuda by Default
- Does this work anymore? HOT 2
- Vector Concatenation Question
- InferSent for Spanish
- ModuleNotFoundError: No module named 'models' HOT 1
- Infersent for Indian language
- How we fine tune inferSent for calassification problem like sentiment analysisi?
- KeyError: '</s>'
- extract features Infersent error HOT 1
- inconsistent sentences length causes encoding failure
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.
from infersent.