Comments (3)
Hi, thank you for your interest! this implementation is the same as it is in the original FGFA repo. And in the paper it also says "By default, we sample 2 frames in training and aggregate over 21 frames in inference.", so in training, the current frame is not accumulated. But it could be sampled by random sampling.
from mega.pytorch.
Hi, Thank you for your answer! I also notice this in the original paper. By the way, I have another question. I notice both your reimplementation and official MXNet code multiply the flownet output by 2.5. But in original flownet code, I have not seen this line. Could you tell me why the output flow need to multiply by 2.5?
from mega.pytorch.
I just follow the implementation of the original repo so I also don't know why :) Maybe you should ask the author of FGFA paper or you could try to remove the 2.5 factor and see whether the performance will drop.
from mega.pytorch.
Related Issues (20)
- About reproducing FGFA results
- How to plot the loss/P-R curve
- How to aggregate the results of local aggregation and LGlobal aggregation?
- A severe BUG in dataloader (mega_core/data/datasets/vid_mega.py)
- I have encountered a problem when using my own data set for training and evaluation. HOT 1
- there was a probblem using my own datasets:RuntimeError: Sizes of tensors must match except in dimension 3. Got 425 and 423 (The offending index is 0) HOT 3
- TypeError: __call__() takes 2 positional arguments but 3 were given HOT 1
- How to train with ONLY VID?
- i test the dff(backbone is resnet101),but the AP50 is 66.58,is much lower than you publish,who can tell why?
- why use the DET datasets?
- when i use 1 gpu training, how to change the iters、step、lr thank you
- windows mmdeploy SDK构建失败
- Can I change the backbone of MEGA? I try to use SWIN,VIT,VIG as the backbone,but I got 0.01% Map.
- failed running python setup.py build develop for mega.pytorch HOT 7
- apex version not match pytorch version 1.3 or lower HOT 3
- 求助大佬们,未修改代码,直接跑的,结果全是0 HOT 4
- Bug Question about validation while training
- INSTALL.md Problem HOT 1
- Dataset unavailable
- ImportError: DLL load failed: 找不到指定的程序。
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 mega.pytorch.