Comments (2)
yikang-li
commented on August 13, 2024
As I told in README.md, I usually train the model with the default config. Then using "--resume" to train 10 epochs or more. From my experience, 30 epochs are enough to get comparable results.
from factorizablenet.
cao-nv
commented on August 13, 2024
Sorry for replying in a closed issue, but how long did it take you to train the RPN and the full network with the batch size 1?
I'm training the full network in multi GPUs (8 Titan Xp), then I found that the batch time is too long 3.94s. With this batch time and your normal training set on Visual Genome, it takes me about 6 hours to complete an epoch. Is that training time normal?
Looking forward to hearing from you soon.
from factorizablenet.
Related Issues (20)
- image not getting loaded HOT 6
- Segmentation fault due to _C.so file HOT 2
- Dataset for Accuracy reported
- Regarding use of regions and caption_rois HOT 1
- Using factorizable_net_v4.py forward_evaluate() to evaluate unannotated images HOT 1
- config file HOT 3
- Generate scene-graph for a single test image. HOT 3
- Evaluation Warning: underflow encountered in multiply
- when evaluate_object,error occured HOT 1
- how to evaluate in new image without ground truth xml? HOT 18
- Anyway to run on win10 machine?
- error when training HOT 2
- Who has the Scene Graph of coco dataset , can you publish it,thanks a lot
- How much times the clustering for objects and subgraphs ? One?
- We define its confifidence score as the product of the scores of the two object proposals?
- avg-pooled features (m × 515×1×1)
- I think maybe the code can implement the remand of producing the features by assigned locations boxes
- Missing Function "python_eval" HOT 6
- The link for VRD dataset is broken
- the link of the VRD dataset is broken, where can I get the images
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 factorizablenet.