Comments (3)
Got it. So I guess the gradient of the loss function won't be backpropagated through time through dynamic templates, since they are sampled in an indifferentiable way. This is still confusing, during inference dynamic templates are chosen by the network, but during training they seem to be independent of other parts. Will such a gap affect accuracy?
from stark.
Hi, we use get_frame_ids_trident function to sample the initial template frame, search region frame, and the dynamic template frame. To be specific, we first randomly sample two frames as the initial template and the search region. The interval between them is ranged from [0, L] (L is the sequence length). Then we sample an extra frame as the dynamic template. The interval between the search frame and the dynamic frame is ranged from [0, max_interval] (here we set the default max_interval as 200)
from stark.
Yep, during the training stage, the dynamic template is sampled heuristically rather than using the network. Ideally, the training process should be completely consistent with the test process, which is in a sequential manner. However, due to the memory limit, we don't implement backpropagation through time.
from stark.
Related Issues (20)
- the checkpoint file of stark-st1 link has expired HOT 2
- Where to download STARKST_ep0500.pth.tar ? HOT 2
- How to create the data folder with all the datasets on it?
- only one dataset HOT 2
- which type of query was used?
- The link of STARKST_ep0500.pth.tar of stark_ref-baseline is invalid in STARK_LT HOT 13
- 尝试通过TensorRT推理Stark模型
- 使用TensorRT推理STARK-Lightning onnx模型 HOT 5
- about lmdb HOT 1
- stage2 class_loss降不下去
- 似乎所有的预训练模型链接都无效了,可以重新发一下吗?我的qq邮箱[email protected]
- 我将STARK-S50的backbone换成了RepVGG-A0精度很低
- Problem of Training for Stark-Lighting-X-trt HOT 1
- 目标走出视野后仍在跟踪
- 1
- How to get score or confidence from onnx
- 模型下不下来
- Some questions about AR(Alpha Refine).
- Qualifications
- checkpoint 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 stark.