Comments (4)
Well, as far as I decipher:
The first digit is always 1 and it denotes that this frame is present (and not absent that is). Not really helpful indead.
The other 2 together reveal the sampling of all frames from each video. The intention is to keep exactly 15 frames from each video. The final number is the total number of frames of this particular video and the penultimate number is id of the sampled frame.
For example for the 1st video (ILSVRC2015_train_00000000) the 1st 3 lines are:
train/ILSVRC2015_VID_train_0000/ILSVRC2015_train_00000000 1 10 300
train/ILSVRC2015_VID_train_0000/ILSVRC2015_train_00000000 1 30 300
train/ILSVRC2015_VID_train_0000/ILSVRC2015_train_00000000 1 50 300
which means 300 frames are present and the 1st sampled frame is the 10th one, the second the 30th etc.
from flow-guided-feature-aggregation.
@PCML-WangZhe
Have you known the meaning of the last three numbers?I also have the same question!
from flow-guided-feature-aggregation.
@ Now I want to train own data which have 'person' label .But I do not know how to do my data as author's train data and to download my data using author's code.Can you tell me how to do? Thank you very much.
from flow-guided-feature-aggregation.
@eypros
Hi~ About the penultimate number , I notice they have different intervals when TotalFrameNumber changes. Do you know how the penultimate number are set(calculated)?
Thanks!
from flow-guided-feature-aggregation.
Related Issues (20)
- How to get mAP by motion
- Installing mxnet using pip works! HOT 5
- error in function vid_eval_motion: What is motion_iou ?? HOT 4
- resnext backbone version
- where is ILSVRC2015_DET? HOT 2
- ILSVRC2015 DET. Whats that for?
- About config.py HOT 1
- 作者 你好 有pytorch版本的吗
- People Detection
- the reason why imagenet_det is needed.
- pip install mxnet-cu100 == 1.5.0
- make -j4
- 数据读入的时候好像是乱序的,感觉并不是前后9帧的特征融和
- 关于光流的方向
- How to organize the ImageNet dataset for training? HOT 3
- Regarding Batch Size for training and testing
- How to visualize the output after testing the data?
- 运行sh ./init.sh出错
- Killed during training processing
- How can I perform mixed training with DET and VID datasets, considering that the DET dataset does not consist of consecutive frames?
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 flow-guided-feature-aggregation.