Comments (5)
The released code has some slight difference compared to those hyper-parameters provided paper (we change the weight of the loss when we release the code). Currently, you could simply use the provided config file. If you want to use larger batch size, just adjust the learning rate following linear scaling rule and also scale the scheduler to train for the same number of epochs.
from alphaction.
Thanks for your reply! As I'm reproducing the results in Pytorch, I cannot directly use the config file provided for training. One question is how many epochs I should train for? I'm not sure how to convert the number of iterations in your config file to the number of epochs (one epoch refers to one scan of the whole dataset). Thanks.
from alphaction.
The training set includes about 200,000 video clips, so for the iteration number in the config file, epoch ~= 16*iteration_num/200000. I recommend you to reproduce the results following this codebase, since not all details are clearly clarified in the paper (e.g, the focal loss, the weight of each loss).
from alphaction.
Thanks for your reply!
from alphaction.
The training set includes about 200,000 video clips, so for the iteration number in the config file, epoch ~= 16*iteration_num/200000. I recommend you to reproduce the results following this codebase, since not all details are clearly clarified in the paper (e.g, the focal loss, the weight of each loss).
hi, I want to know that when evaluating the loss, why the weight of pose loss is 1.2 rather than 14.0?(the weight of object loss is 49.0 and the weight of person loss is 17.0). Thank you!
from alphaction.
Related Issues (20)
- INSTALL.md Issue when running pip install -e . HOT 4
- Train on custom dataset HOT 1
- Init weight for DenseSerialIAStructure
- RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation HOT 2
- The detection person box of UCF24 using Faster RCNN in this paper
- TypeError: conv3d() received an invalid combination of arguments HOT 5
- Problem during installation
- No module named 'alphaction._custom_cuda_ext'
- THC/THC.h: No such file or directory HOT 1
- Access to download the data HOT 1
- key frames HOT 4
- windows system HOT 1
- boxes annotation HOT 1
- json files HOT 1
- Duplicate Modle Zoo to Baidu Netdisk
- Can we use this for JHMDB dataset ?
- difference between the realtime and non-realtime inference
- Error while Training HOT 1
- OSError: cannot open resource
- size mismatch HOT 2
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 alphaction.