Comments (4)
Thanks very much for your interest in our work. Our MobileSAM uses exactly the same lightweight decoder (including pretrained weights) as the original SAM. The decoder is less than 4M, and in total our MobileSAM has less than 10M parameters. We will update our code so that the user can directly use our lightweight MobileSAM without the need to download sam_vit_h (Stay tuned!). If you have more questions please let us know.
from mobilesam.
So I cloned the repo and worked through the notebook. Do I understand correctly that there's a lightweight image encoded based on TinyViT, but you still need to use the fullsize SAM decoder? I had to download the
sam_vit_h_4b8939.pth
file, which is 2.4GB.Am I using this wrong? Or are there smaller decoder models?
We have just updated the code for addressing your raised issue. Thanks for your interest in our work again!
from mobilesam.
Excellent, I'll pull your changes and take a look today. Great work, thanks for sharing!
from mobilesam.
Excellent, I'll pull your changes and take a look today. Great work, thanks for sharing!
Thanks for your interest in our work. Since your issues are addressed, we close it. Please feel free to raise new issues.
from mobilesam.
Related Issues (20)
- Why is the segmentation effect bad after full fine-tuning training? There are also pseudo-pixel grids in the segmentation result
- a issue of multiple boxes input
- Can you convert the code to tensorflow? HOT 1
- Q for computation resources between coupled and decoupled distillation HOT 1
- Would you please upload v2 model files
- Would you please upload the pretrained yolo model
- Finetuning on 24GB 1 GPU training parameters
- MobileSAM-v2 occupied ~18GB of GPU
- Getting mobileSAM into a format that runs on mobile (tflite, torchscript) HOT 4
- Can the image size only be 1024X1024? HOT 1
- Cannot convert ObjectAwareModel to onnx
- mobilesamv2 bug HOT 2
- encoder_embed_dim,encoder_depth,encoder_num_heads=16,encoder_global_attn_indexes参数是什么?
- How to use it with text prompt?
- Box prompts demo
- "bash ./experiments/mobilesamv2.sh" does not work on Mac M1 HOT 2
- Performance definition in Mobilesamv2 paper
- Why is it slow to segment everything? Is there a good solution?
- When available the train code HOT 2
- More than one bounding box
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 mobilesam.