Comments (3)
Memory consumption comes from two parts: 1) a constant cost used by the image model and the propagation model (scale with chunk size and resolution), and 2) a linear cost w.r.t. to the number of objects (and resolution) in memory.
It seems like that (2) is giving you problems. Can you try reducing max_num_objects
?
Not sure if you have already, but specifying --amp
also helps a lot.
from tracking-anything-with-deva.
When using the max_num_objects
argument some of the output frames end up black and I get the output:
Tracking-Anything-with-DEVA/deva/inference/segment_merging.py:118: UserWarning: Number of objects exceeded maximum (--max_num_objects); discarding new objects
warnings.warn(
Tracking-Anything-with-DEVA/deva/inference/inference_core.py:69: RuntimeWarning: Empty object mask!
warnings.warn('Empty object mask!', RuntimeWarning)
Tracking-Anything-with-DEVA/deva/inference/inference_core.py:95: RuntimeWarning: Trying to segment without any memory!
warnings.warn('Trying to segment without any memory!', RuntimeWarning)
Can this situation be imporved?
I was able to make it work tho with --SAM_NUM_POINTS_PER_SIDE 32 --SAM_NUM_POINTS_PER_BATCH 32
and 2k input images.
from tracking-anything-with-deva.
This looks weird. Can you provide more info? Like when does it become blank? Can you post the output video?
from tracking-anything-with-deva.
Related Issues (20)
- 0-5 represents the target? HOT 4
- TrustImageSeg Inference HOT 1
- yolo_world with DEVA HOT 2
- U-net with DEVA HOT 13
- Parameter Adjustment in Automatic Mode and Objects Reappearance Problem HOT 2
- Just want to confirm! HOT 5
- Just want to confirm! HOT 1
- extracting mask and bbox HOT 1
- RuntimeWarning: Trying to segment without any memory! HOT 7
- something about data format HOT 27
- How to get subpart/part/whole-level segmentation like SAM? HOT 2
- The mask in example HOT 3
- Something about the provided detection on VIPSeg HOT 3
- SAM for the training sets of YouTube VOS and Davis 2017 HOT 2
- RuntimeWarning: Trying to segment without any memory HOT 5
- Subsampling BURST when evaluating HOT 1
- Can deva be extended to video semantic segmentation and video instance segmentation tasks? HOT 4
- Hello, I found that this method matches black results when there are only two images of this input.。。 HOT 1
- reading data is particularly slow HOT 2
- Will changing the batch size from 16 to 18 and running with 6 cards result in performance loss? 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 tracking-anything-with-deva.