Comments (2)
I pre-process the annotations and word embedding by command line.
The corpus files consist of six parts: 1. annotations of training split represented by word index; 2. annotations of validation split represented by word index; 3. annotations of test split represented by word index; 4. the mapping from a real word to a word index; 5. the mapping from a word index to a real word. 6. pretrained word embedding from GloVe-840B-300d.
I think you can recreate such pickle with the help of my description and the provided word mapping.
The reference pickle files consists of three parts: 1. the human-readable ground truth of training split; 2. the human-readable ground truth of validation split; 3. the human-readable ground truth of test split.
The preprocess codes of npy files have been provided in the repository.
from semantics-assistedvideocaptioning.
Thanks a lot
from semantics-assistedvideocaptioning.
Related Issues (15)
- msrvtt_resnext_eco feats HOT 2
- If the test set is used for training tag_net? HOT 1
- Nan Values Generated by the tagging network HOT 1
- about semantic detection network generate meaningful semantic features for videos HOT 1
- Tagging checkpoint
- About test
- ECO features
- Question about MSR-VTT. HOT 5
- implementation detail HOT 1
- 请问sentence length loss在代码中体现在哪里 HOT 3
- 关于ResNeXt101和ECO提取特征的疑问以及用于训练语义检测网络的两个npy文件 HOT 4
- 您好,请问增加candidate tags的数量是否还会提高指标? HOT 1
- how to get close mAP as the newer version 《A Semantics-Assisted Video Captioning Model Trained with Scheduled Sampling》 HOT 1
- Dataset Split
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 semantics-assistedvideocaptioning.