Comments (3)
Great!
I think if this encompasses loss logging (under the constraints that sensor values are available for the specified loss), that will be quite useful.
Sounds good. In principle we could just allow people to pass in a list of losses that they'd like to have recorded during testing, perhaps that's the most robust solution as the user could also record losses not included during training.
from allenact.
👍
I've implemented this at some point on an old branch. I think the main roadblock to having this on by default is that we cannot expect that certain sensor readings are available in the validation / test sets. For instance, if we train a model with imitation learning, it is very possible that we do not have expert actions for the test set. Would it be sufficient to be given the option to define new, custom, logable values in the experiment config?
from allenact.
I think the main roadblock to having this on by default is that we cannot expect that certain sensor readings are available in the validation / test sets. For instance, if we train a model with imitation learning, it is very possible that we do not have expert actions for the test set.
I see. Makes sense.
Would it be sufficient to be given the option to define new, custom, logable values in the experiment config?
Yes. I think this will be useful. However, if it's only restricted to metrics that only utilize task-level information -- path taken, etc. to compute new metrics -- then I guess this would only slightly make things easier for the user in the sense that the user doesn't have to modify the task definition by themselves. I think if this encompasses loss logging (under the constraints that sensor values are available for the specified loss), that will be quite useful. But I do see your point that this might not generalize well to all settings -- might be easier for auxiliary losses that don't necessarily rely on the specific task definition (CPC|A, inverse / forward dynamics) as opposed to others.
from allenact.
Related Issues (20)
- When I ran the Room Rearrangement task experiment, EOFerror appeared HOT 2
- Visualization part of the tutorial 'Using a pre-trained model' has error HOT 4
- Fix for vulnerable packages in the pip dependencies of this project HOT 1
- Cannot run "gym_mujoco_tutorial" HOT 1
- Visualize a policy from a checkpoint HOT 3
- Code is getting stuck after few iterations HOT 10
- Some depth values are not within the 0-5 range for RoboTHOR's DepthSensorThor HOT 2
- procthor HOT 4
- How to install and run habitat plugin HOT 1
- How to create custom dataset for object navigation and rearrangement? HOT 1
- Unable to access testing scenes in RoboTHOR HOT 7
- TimeOut error when attempting to run pre-trained RoboThor model checkpoint HOT 11
- How to create custom objectnav dataset HOT 1
- AttributeError: 'RolloutBlockStorage' object has no attribute 'memory' HOT 1
- pdb support HOT 1
- The URL link to download the dataset is invalid HOT 2
- Cannot experiment because my internet is slow (timeout) HOT 4
- Only one valid platform is required to run AI2-THOR HOT 10
- Cannot reproduce the performance of EmbCLIP on the ObjectNav task of the RoboTHOR HOT 2
- Displayconnection error HOT 1
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 allenact.