Comments (4)
@jaxony Thank you very much for your interest in the project! I will compile a list of TODOs in detail later this weekend. For now, we may consider some simple changes:
- Support more datasets: PRID, iLIDS, GRID, etc. May refer to this list
- Combining all the datasets together to train models. (This mainly helps for applications)
- More neural network models: ResNeXt, Inception-ResNet-v2, Shake-shake regularization, SqueezeNet, MobileNet, ShuffleNet, etc.
- More metric learning algorithms: XQDA, Null Space Projection, etc.
- Evaluation with multi-crop and multi-scale input images
- Improving the documents
Some more complicated ones include:
- Adding a reranking module with a factory of different methods
- Refactor the feature_extraction module to make it support handcrafted features: LOMO, GOG, etc.
- Support siamese networks with joint feature embedding
Any comments are welcome!
from open-reid.
@Cysu Thanks for the list! It's definitely enough to get started on. I'll start with the simpler changes.
from open-reid.
Hi @Cysu, I implemented a ShuffleNet over the weekend to add to open-reid. Unfortunately I don't have a good GPU to train on ImageNet to see if it even works. I wrote some basic tests, so the model's output size and operations should be correct.
I was hoping maybe you could test it out if you have a good GPU on hand?
from open-reid.
@jaxony That's great! Could you please open a pull request, so that I can checkout locally to test it?
from open-reid.
Related Issues (20)
- Dependencies - setup.py
- is it generalised
- DukeMTMC dataset can't be downloaded HOT 2
- Problem with the file examine.softmax_loss.py HOT 5
- It can not converge on non-pretrained model HOT 1
- Train with only 1 camera in duke
- Viper is missing HOT 2
- TypeError: Can't instantiate abstract class Euclidean with abstract methods get_metric, score_pairs HOT 1
- How much video memory do I need? HOT 1
- DukeMTMC result reporting
- OIM loss HOT 1
- OIM loss initialize error
- IndexError: invalid index of a 0-dim tensor. HOT 6
- RuntimeError: zero-dimensional tensor (at position 0) cannot be concatenated
- RuntimeError: Duke
- TypeError: Can't instantiate abstract class Euclidean with abstract methods get_metric, score_pairs HOT 2
- something miss with sort and match? HOT 1
- AssertionError: Torch not compiled with CUDA enabled
- Oim Loss with 'NAN' problem
- eep q learning
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 open-reid.