Comments (4)
Dear @z7r7y7 ,
you are confusing two things. The argument synt_background
refers to images that you can sample from for synthetic images to replace their background. If you are working with the LMO dataset you have images that are synthetically rendered and thus have no background, i.e. just a black background. For the sake of data augmentation we allowed for the data sampler to sample an image and use it as a background instead of a blank background.
To summarize, the background data for synt_background
should be a directory containing random images from which you can sample. For example, I use the validation set of the MSCOCO dataset.
However, you found a bug where it tries to sample from the background images, but it can't if there none provided. I will fix it immediately to raise a warning in that case.
Best,
Thomas
from poet.
Thank you very much for your response, and the issue regarding the background has been resolved!
While running the code for the object detection model using Mask R-CNN, I encountered another problem in the "poet/models/backbone_maskrcnn.py" file, specifically in lines 98-112, where the variable "img_predictions" is generated containing information about the bounding boxes, labels, and scores.
I noticed that in lines 101-106:
if self.obj_id_map is not None: if cls.item() in self.obj_id_map.keys(): new_cls = self.obj_id_map[cls.item()] box = torch.hstack((box, torch.tensor(new_cls, dtype=torch.float32, device=device))) else: box = torch.hstack((box, cls)) img_predictions.append(box)
when adding the label information (cls) to the boxes, if the "obj_id_map" is not empty but the label does not belong to the "obj_id_map", resulting in a 1x5-dimensional "box" without label information, while in other cases, it is a 1x6-dimensional "box" with label information. This dimension mismatch can lead to an error in torch.hstack in line 112:
img_predictions = torch.stack(img_predictions)
Therefore, I think it may be necessary to add a conditional statement to collect only the box information with dimensions of 1x6.
from poet.
You are definitely right. The model might predict objects that are not in the object_id_map.
With the most recent commit, I implemented it as a skip if the detected object is not of "interest".
Hope it works now and thank you for raising this issue!
Best,
Thomas
from poet.
Closed due to inactivity. Feel free to open the issue again.
from poet.
Related Issues (20)
- Evaluation of PoET in distributed training mode
- How to run PoET in inference mode. HOT 12
- Provide Dockerfile HOT 6
- About FasterRcnn detector HOT 1
- Train using custom dataset HOT 9
- How to import the LM-O dataset HOT 9
- Was the LMO dataset also trained for 50 epochs? HOT 1
- Question about two missing parameter files in main.py HOT 1
- YCB-Video dataset link HOT 2
- Loss is NaN in training HOT 5
- Transfer Learning
- Evaluation results very bad HOT 4
- Great Repository HOT 1
- Details about training ycbv with yolo HOT 2
- fail to pull docker images HOT 2
- Question for the ycbv2poet.py HOT 3
- Questions about visualization or demo script HOT 2
- Demo script for inference mode HOT 23
- Distributed Training in Docker HOT 5
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 poet.