Comments (7)
@SonrLax Because when MEGA makes a prediction, it doesn't rely only on just one image, so the demo is not directly applicable. I need to preprocess the whole video into a queue and sequentially process them. It's not hard but a bit tricky. :)
from mega.pytorch.
Any help you can give?
Thanks
from mega.pytorch.
Sorry for late reply! You may refer to mmdetection to see how they inference on a piece of video and adjust some code of this repo accordingly to achieve the behavior you want. After the NIPS ddl I will try to add demo to enable inference on video files but currently I have no time :( Hope this piece of message would help!
from mega.pytorch.
I will take a look at mmdetection code and try to do it myself.
In the meantime, it will be great that you can add one after NIPS in case I am not able to do it
Thanks,
from mega.pytorch.
@Scalsol Since MEGA is based on maskrcnn_benchmark, why not refer to demo ? Just curious.
Thanks !
from mega.pytorch.
I've added demo for visualization, closing this. Feel free to reopen it if the visualization doesn't work :)
from mega.pytorch.
!hi, I get segmentation fault whenever i try to do demo on my video, or i get Imagelist not scriptable any help please ?
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.