Comments (6)
Densecap evaluates the results in their box coordinates system. For example, we make change to the output boxes to adapt their coordinates as shown here:
Line 100 in 39b33db
Did you save results which go through the above code? If not, please follow it to rescale the box.
from grit.
Line 100 in 39b33db
Yes, I run the
python train_net.py --num-gpus-per-machine 8 --config-file configs/GRiT_B_DenseCap.yaml --output-dir-name ./output/grit_b_densecap --eval-only MODEL.WEIGHTS models/grit_b_densecap.pth
command to get the json result of predictions on VG, which has gone through process() to resize the boxes.
from grit.
Perhaps the performance drop is caused by this?
from grit.
The densecap repo should not have evaluation issues. We successfully obtain our results by only adding a read function.
Perhaps you didn't get it right because of the box coordinate format. Our saved json is in (lefttop_x, lefttop_y, w, h), while densecap uses (center_x, center_y, w, h). Please make sure to convert to densecap format and try again.
Apart from this, I think there are no other places that could make a difference in the results.
from grit.
The densecap repo should not have evaluation issues. We successfully obtain our results by only adding a read function.
Perhaps you didn't get it right because of the box coordinate format. Our saved json is in (lefttop_x, lefttop_y, w, h), while densecap uses (center_x, center_y, w, h). Please make sure to convert to densecap format and try again.
Apart from this, I think there are no other places that could make a difference in the results.
Thank you so much!
from grit.
@Wykay @JialianW Hi
I have a similar issue as @Wykay had before! I appreciate your help
In your evaluation code, are you using denscap dataloader to get the ground truth bounding boxes and captions?
What is the format of the ground truth bounding boxes in GRIT test.json and train.json files? Is it (x_topleft, y_topleft,w,h) or (xc,yc,w,h) or (x1y1,x2,y2)?
from grit.
Related Issues (20)
- Question about training on custom data HOT 1
- Can you provide the performance based on the GT boxes? HOT 3
- KeyError: 'object_description'
- No module named 'detectron2' HOT 2
- Support for Batch-Inference HOT 1
- Generate Caption on my own boxes HOT 1
- Installation instructions seem out of date HOT 1
- eval code HOT 1
- Output the result in the format of text
- third_party project gitmodules HOT 1
- CUDA out of memory
- Inference Issue: Model Fails to Detect Guns in Scene
- Fine-tuning GRiT
- Questions about multi-node deepspeed launcher HOT 1
- Batch size Configuration HOT 1
- Question about the training time HOT 4
- Dense Captioning Evaluation on VG Dataset HOT 10
- Willing to share the original annotations of Visual Genome dataset ? HOT 2
- Larger ViT backbone for dense captioning 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 grit.