Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
RNN4ridesharing
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Container registry
Model registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Filippo Bistaffa
RNN4ridesharing
Repository graph
Repository graph
You can move around the graph by using the arrow keys.
batch_gpu_copy
Select Git revision
Branches
4
added_features
batch_gpu_copy
master
default
protected
oscar
4 results
Begin with the selected commit
Created with Raphaël 2.2.0
27
Jul
22
21
20
9
Mar
15
Feb
10
6
5
4
30
Jan
27
26
24
23
22
21
20
17
16
14
Merge branch 'oscar' of https://gitlab.iiia.csic.es/filippo.bistaffa/rnn4ridesharing into oscar
oscar
oscar
VarTrain
Delete count_requests.py
Counter Finale
Count
Data
Merge branch 'oscar' of https://gitlab.iiia.csic.es/filippo.bistaffa/rnn4ridesharing into oscar
Scripts folder
Delete test.txt
Manhattan.csv
Test commit on new branch
Better compatibility
master
master
Removed useless import
Updated code to save models
Check if batch size is a multiple of the number of GPUs
Save model architecture
Better model saving
ReLU output layer
Save arguments and epoch in state dict
Renamed model
Bug fixed
Corrected comment
Remove dots from message
Merge branch 'master' of gitlab.iiia.csic.es:filippo.bistaffa/rnn4ridesharing
Print number of samples per second as performance measure
Catch imbalance warning
Pin memory + better code
batch_gpu_copy
batch_gpu_copy
Copy entire batch at once rather than individual sequences
Do not copy entire input to GPU
Print memory summary for each device
Print model
Multi-GPU
Remove hidden tensor initialisation
Show number of batches per second
Added option to save the model each epoch
Changed default number of epochs
Nice output + ETA
Add timestep, weekday, and holiday features
added_features
added_features
Changed default forecast horizon
Print input size
Loading