Comments (2)
I see both options in the literature: Using one single learning rate for all (e.g. Distance Sampling/Marginloss paper: https://arxiv.org/abs/1706.07567, Semihard Sampling: https://arxiv.org/pdf/1704.01285.pdf) or different learning rates (Hardness Aware DML https://arxiv.org/pdf/1903.05503.pdf). In addition, I examined both options and found it to make little to no difference, as I could replicate most baselines results regardless.
However, for those that require this option, I have just added it in the latest update. Simply set the flag --fc_lr_mul
to the value you want to multiply the embedding layer with, and you are good to go :). Thanks for the suggestion!
from deep-metric-learning-baselines.
Awesome, thanks!
from deep-metric-learning-baselines.
Related Issues (20)
- Version of in-shop dataset HOT 1
- Issue when loading In-Shop Clothes Dataset HOT 2
- is the file 'pretrainedmodels.py' missing? HOT 2
- A question to ask HOT 1
- The "BaseTripletDataset" HOT 1
- Because the use of faiss, the windows is not supported HOT 2
- Question on Proxy-NCA HOT 3
- RuntimeError: CUDA out of memory. HOT 2
- question about code in "googlenet.py" HOT 2
- Question about method 'semihardsampling' of class 'Tuplesampler' HOT 1
- Add Person Re-Identification Dataset HOT 1
- ModuleNotFoundError: No module named 'pretrainedmodels' HOT 2
- about the organization of Cars196 HOT 1
- Error while training
- How to make it an inference model?
- In-Shop Clothes Retrieval HOT 1
- Sampler --> TripletSampler? HOT 2
- resizing images to 256x256 HOT 2
- Evaluation on SOP took forever 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 deep-metric-learning-baselines.