Comments (5)
Hello,
I would train different models for different vessel types.
from geotracknet.
Hy @supercrazysam
after you have 3 pkl files from preprocessing. you need to "calculate_mean" of the training dataset before you run the training code.
after you have the mean.pkl just run the training, then save_logprob(for valid and test dataset), local_logprob(for valid dataset) and contrario_detection(for test dataset).
the thing you have to pay attention is in "calculate_mean.py" the lon_bins, lat_bins, sog_bins, and cog_bins is defined hard coded. but in flag_config.py the authors calculate it by ratio of the ROI compared to the grid resolution that wanted (in this code the resolution of lat and lon id 0.01).
So I think you should make the lat_bins and lon_bins on "calculate_mean.py" to be a ratio too
Sorry for the late reply. hope this can help you..
have a good research
from geotracknet.
oh @dnguyengithub I forgot to thank the super authors. really, you helped me a lot. thanks man
from geotracknet.
You're welcome.
Good luck with your research
from geotracknet.
Hi, @MasaruPutut, I heard you successfully used the code on your own dataset.
I have modifed the csv2pkl.py and data_preprocessing.py to produce the 3 pkl data files and 3 corresponding pngs.
In the 3 pngs, I can see filtered tracks in the specified region of interest.
But I am not sure what is the next steps.
What did you do to make it work with your dataset?
What files and what part did you modified?
Are there any things that I need to pay attention to?
Do I need to make the region size (LAT_RANGE, LON_RANGE) on my dataset+pkl, the same as the default trained model?
from geotracknet.
Related Issues (20)
- VRNN Model HOT 1
- contrario detection Issues HOT 3
- Using my own dataset. HOT 15
- Dataset Details HOT 3
- Logits Vs Probs. Are they being mixed up? HOT 2
- Using new dataset HOT 9
- 4 hot vector with dataset HOT 1
- An error when run "save_logprob"
- Tensorflow 2.x version HOT 1
- Environment setup difficulties HOT 5
- GPU Power required to run GeoTrackNet HOT 2
- Suitable Cuda and Graphic card used with environment?
- Validation data explanation / strategy? HOT 3
- Anomaly output metric HOT 3
- ValueError while training the embedding layer HOT 7
- ValueError: ./chkpt/elbo-ct_2017010203_10_20_train.pkl-data_dim-702-latent_size-100-batch_size-1 doesnt exist.
- Inputs for csv2pkl.py HOT 2
- LAT_MIN, LAT_MAX, LON_MIN, LON_MAX Values HOT 1
- 请问这个csv文件在哪里
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 geotracknet.