Comments (3)
I don't know if this use case legitimizes changing the interface.. You could just create a new Embedder-style object for you use case. Could you provide an example or two so we can better understand the motivation?
from flambe.
NLP models that do sequence comparison (the NLI groups comes to mind) are oftentimes implemented with a different encoder object for each compared part. In these cases, the standard flambe implementation will instantiate not only two encoders, but also two embedders - which, again, can result in a waste of GPU memory as embedding matrices can be huge.
from flambe.
Ok this use case makes sense, but I don't understand the change you are requesting. Embedding and encoder are already separated. Embedder links both of them, so you could very easily create a different embedder with two encoders?
from flambe.
Related Issues (20)
- `Script` should support positional arguments HOT 2
- Cannot add custom attributes to a flambe module HOT 1
- Relative paths no longer work for local resources
- Reporting server not logging requests when tensorboard is installed.
- More useful stage dependency graph
- Check cluster compatibility of the yaml config before starting the cluster
- AvgPooling fails even when input dimensions match expected ones. HOT 1
- Richer debug mode HOT 1
- Warning when copying a tensor in the base sampler
- Reporting script can die on the orchestrator HOT 1
- Out-of-the-box experiments with standard datasets HOT 1
- Make `extra_validation_metrics` a key-value mapping rather than a list HOT 1
- RNN (sru) is incompatible with torch 1.3
- Make all Flambe base-models torchscript compatible HOT 1
- No in-built functionality for tracking of metrics during training HOT 3
- Allow pickle for saving checkpoints in Experiment HOT 1
- TaggedScalar instead of Schema when using make_component HOT 1
- Early checks for constructor argument incompatibilities HOT 2
- Better data handling for datasets 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 flambe.