Comments (1)
Thank you for the excellent code. I am wondering if you could share the training config on ActivityNet dataset.
You can refer to the code of ACMNet (https://github.com/ispc-lab/ACM-Net) and transplant our method on their codebase. The config for ActivityNet is as follows:
"dropout":0.7,
"lr":2e-5,
"weight_decay":0.001,
"inp_feat_num":2048,
"out_feat_num":2048,
"scale_factor":10.0, # scaling factor for calculating classification scores
"n_mu":8, # the number of GMM centers
'em_iter':2, # the number of EM iterations
"o_weight":0.8, # the weight of main branch for TCAM fusion during testing
"m_weight":0.2, # the weight of intra-video branch for TCAM fusion during testing
"lambda_b":0.1, # weight of the multiple instance learning head of the classification head (the weight of the Class-agnostic attention head is set as 1.0)
"lambda_att":0.1, # weight of attention normalization loss
"lambda_spl":1.0, # weight of pseudo label loss
from rskp.
Related Issues (12)
- about cuda memory HOT 5
- CUDA error: invalid configuration argument HOT 2
- requirement.txt HOT 1
- Question About Paper HOT 2
- Question about thumos14 dataset and Thumos14reduced dataset HOT 2
- Question About Memory Bank HOT 2
- Question about random_walk part HOT 1
- Features of THUMOS14 HOT 4
- sorry I can't reproduce the result of the RSKP, the best of the map is only 43.7 HOT 1
- how to solve the warning "WARNING batched routines are designed for small sizes. It might be better to use the Native/Hybrid classical routines if you want good performance." HOT 2
- Problem about train on ActivitiNet 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 rskp.