DeepGravity

DeepGravity copied to clipboard

Hello, I was wondering if there might be a small issue on line 203 of the main.py source code? Would it be more appropriate to use _**d2f[d] += f**_ when...

newbie0621

flows.csv link is expired

2

Dear author, could u send me a copy of flows.csv? [email protected]

Jidi123

Just dropping an FYI for the authors/slash any innocent soul that is potentially attempting to apply this methodology to new data. Not only is it impossible to replicate the authors'...

dmolitor

File preprocessing/model execution does not work as expected

4

Awesome project, really exciting and innovative work! In the current master version the project cannot correctly parse new input files and will also fail on the default new york dataset...

j4freeman

how to define the output areas? Is the output area a sector of the study area selected by ourselves or is it generated by the code? I selected the output...

xiang526

New York dataset

1

Hi, I was wondering what period of time this data set is from COVID19USFlows？I download flows.csv without mentioning the time.Thank you!

lawrence1999

About the softmax layer of the model architecture

3

Hello, I am also a researcher on GIScience and human mobility, and I have read your paper about "DeepGravity" published on Nature Communications. It's an excellent and innovative work. And...

sunshineYin

Error when trying to run the code

1

Hi there!, I´m tryng to run the code for the NYC data and getting this error: > --epochs 1 --device cpu --mode train > Train Epoch: 1 [2530/2531 Loss: 671.671570...

fatimavrojas

Hi, thanks for your great work! I have downloaded your code directly, however, I obtained the following performance: Average CPC of test tiles: 0.4445 stdev: 0.1901. It is very different...

Umaruchain