Comments (4)
Hi @xiaoxiaoczw,
The detector weights are in fact frozen already. We fine-tuned the object detector as a first stage and only train the interaction head next. The corresponding code is here.
for p in upt.detector.parameters():
p.requires_grad = False
param_dicts = [{
"params": [p for n, p in upt.named_parameters()
if "interaction_head" in n and p.requires_grad]
}]
Fred.
from upt.
Hi Fred,
Thanks for your quick feedback!
By the way, which pretrained weights do I need to load if I want to train on my own dataset?
from upt.
To get the best performance, you would want to fine-tune the object detector on the custom dataset first, and then train the interaction head. But if the custom dataset has the same set of objects and you don't want to go through the trouble, you can just load the provided detector weights. You can choose amongst the pre-trained MS COCO weights, fine-tuned HICO-DET weights and the fine-tuned V-COCO weights. Which one works the best for you really depends on the dataset similarity. It would be hard to guess without running experiments.
Fred.
from upt.
Thanks for the suggestion!
from upt.
Related Issues (20)
- list index out of range HOT 2
- error when test vcoco HOT 14
- confused about the vcoco dataset HOT 3
- HICO-DET training accuracy problem HOT 2
- A question about v-coco dataset HOT 2
- Detection results, mAP calculation HOT 2
- torch.multiprocessing.spawn.ProcessRaisedException HOT 2
- Multiple loss training code HOT 2
- train HOT 2
- Detected human–object interactions on video HOT 1
- VCOCO Scenario 1 and Scenario 2 HOT 1
- AttributeError: 'Namespace' object has no attribute 'lr_backbone' HOT 7
- list out of range and checkpoint's state_dict mismatch HOT 2
- UPT predicts scenario 1 of V-COCO HOT 2
- Validation set division on HICO-DET HOT 4
- Real-time measurement HOT 1
- GFLOPs and params HOT 1
- Code to visualize attention maps HOT 1
- suppress overconfident objects HOT 1
- VCOCO evaluation HOT 1
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 upt.