Comments (1)
I suspect you are not modifying the word vectors based on vocabulary metric. As illustrated in Fig. 5 in the paper, please apply δ(WMD) after finishing the training. Here, W should be the seen and unseen word2vec inside MSCOCO/word_w2v.txt. Then, please use the modified word vectors to get the unseen probability
from pl-zsd_release.
Related Issues (20)
- The num_classes during training and testing HOT 1
- How to generate a word_w2v.txt file? HOT 5
- How to generate resnet50_csv_50_focal_seen_w2v.h5?Hoping to get your reply! HOT 4
- train/val curve HOT 1
- Error when loading weights, I want to train it on another dataset, and the num_classes is not 65 HOT 1
- for GZSD,when training,classification (Concatenate) (None, None, 65) ? why not (None, None, 80) ?? HOT 2
- The predicted scores are all zero.Have you seen this problem? HOT 4
- Error when run testing code: IndexError: list index out of range HOT 3
- Error when run training code: tensorflow/core/grappler/optimizers/dependency_optimizer.cc:666] Iteration = 0, topological sort failed with message: The graph couldn't be sorted in topological order.
- evaluation of accuracy HOT 1
- Error while running gzsd.py
- Custom dataset
- Problem in running gzsd.py file HOT 1
- Generate vocabulary file for Pascal VOC dataset
- One query regarding docker image
- Train or test with cpu
- How to generate embeddings for COCO classes with multiple words?
- How to predict objects of a custom category?
- How was the file word_w2v.txt generated?
- Question about vocabulary_w2v.txt and word_w2v.txt
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 pl-zsd_release.