Comments (3)
I am afraid we cannot give a definite answer to your question, since we trained models on different machines. What is common that all models were trained on single GPUs (such as GTX 980, GTX 980, Tesla K20, Tesla K40, Tesla P100 PCI-E). Below is very general summary on run times for each task:
- In-hospital mortality - training in-hospital mortality prediction task is the easiest and takes at most 2 hours.
- LOS and Decompensation - if deep supervision is disabled then decompensation and length of stay models will require a lot of time to get the best performance. Usually it takes about 1-2 days. If deep supervision is enabled, then it will take at most one day.
- Phenotyping - getting the best performance on the phenotyping task requires 4 days, but you can get very close score (0.773 AUC score) in just 6 hours.
- Multitasking - training multitask models takes from 4 hours to 3 days depending which task is the most important for you.
A common rule for all models of all tasks is that when you have high dropout rate (>= 0.3) the model will overfit much later (2-4x more epochs) compared to the same model with zero dropout, but eventually will give better score on the test set. This is why getting the best performance requires a lot of training, while you can get a bit worse performance comparatively very quickly.
from mimic3-benchmarks.
Can we close this issue?
from mimic3-benchmarks.
Thanks for the reply! Will close this issue.
from mimic3-benchmarks.
Related Issues (20)
- Question about origin of hcup_ccs_2015_definitions.yaml HOT 2
- How to get ICD9-code according to each timestamp for per patient? HOT 1
- AttributeError: module 'keras.backend' has no attribute 'observe_object_name' HOT 1
- No such file 'data/root/85404/stays.csv'
- ValueError: Could not interpret optimizer identifier: 0.9 HOT 2
- hcup_ccs_2015_definitions.yaml issue
- ValueError: '0' is not in list
- How to trace back array entries to the actual features used?
- Mismatch between DEATHTIME and OUTTIME
- requirement.txt does not work HOT 1
- Request to publish repository in papers with code HOT 1
- replication of model prediction - deviation of ~2% random seeds missing
- Overflow in int64 addition HOT 5
- the imp module is deprecated in favour of importlib
- ValueError: Failed to find data adapter that can handle input HOT 1
- ValueError: time data '2109-03-20' does not match format '%Y-%m-%d %H:%M:%S' HOT 1
- Project dependencies may have API risk issues HOT 1
- Rename files with colon in the name for Windows compatibility
- ValueError: Use `.rename` to alter labels with a mapper.
- ihm.pkl files differ and lot of missing values in an episode HOT 6
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 mimic3-benchmarks.