stanford-navlab / deep_gnss Goto Github PK
View Code? Open in Web Editor NEWRepository for GNSS-based position estimation using a Deep Neural Network
License: MIT License
Repository for GNSS-based position estimation using a Deep Neural Network
License: MIT License
Hi,
Uploading Pixel4_derived.csv…
ground_truth.csv
When I use "2020-06-11-US-MTV-1" (attached) collected by Pixel4 to train your neural network, I get the error "ValueError: No objects to concatenate"
For your reference:
`Processed file not found. Chunking and saving data for 2020-06-11-US-MTV-1/Pixel4
Traceback (most recent call last):
File "train_android.py", line 96, in main
dataset = Android_GNSS_Dataset(data_config)
File "/home/ling/Documents/GitHub/deep_gnss/src/correction_network/android_dataset.py", line 69, in init
self.chunk_n_save(_path, save=True)
File "/home/ling/Documents/GitHub/deep_gnss/src/correction_network/android_dataset.py", line 289, in chunk_n_save
chunk_df = pd.concat(chunk)
File "/home/ling/miniconda3/envs/deep_gnss/lib/python3.8/site-packages/pandas/core/reshape/concat.py", line 285, in concat
op = _Concatenator(
File "/home/ling/miniconda3/envs/deep_gnss/lib/python3.8/site-packages/pandas/core/reshape/concat.py", line 342, in init
raise ValueError("No objects to concatenate")
ValueError: No objects to concatenate
Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.
`
Weights for trained networks can not be found
Hey there,
Thank you for sharing your Deep GNSS codes.
I tried to run it from scratch. According to your guide, I tried to install the conda environment using conda env create -f deep-gnss.yml. But there seems to be no such a file. Should I use the environment.yml instead?
Hello:
Recently, I read your article titled ‘Improving GNSS Positioning using Neural Network-based Corrections' which is a handsome work, so I also learned relevant codes. Meanwhile, I found that this article was quoted in the article 'Designing Deep Neural Networks for Sequential GNSS Positioning'. I was very interested in it and immediately learned it. Hence, I would like to consult you if the code of this article will be released in the near future. I really want to study the code of this paper. Looking forward to your reply, thank you very much!
Yours Sincerely!
Hello:
It is a really cool work to connect the work between GNSS and DNN. When i try to reproduce the results of the paper, I found that the link of weight file is invalid. could you send the file of weight file to me? Thank you!
Yours Sincerely!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.