Comments (3)
This is Code reference abrove in extractor_sd.py
from sd-dino.
Hi, thank you for your interest in our project. I'd be happy to clarify the code behavior:
The inference code is designed for a batch_size
of 1
for simplicity, hence N
is always 1
, and tensor[0]
is equivalent to tensor.squeeze(0)
. This doesn't discard any other samples since there is only one sample in the batch.
For PCA implementation, please note that the implementation of the PCA used in our default setting is actually the co_pca
function in utils_correspondence.py. The pca_process
function here is retained for completeness but may not be the one used in our default setting.
Feel free to ask if you have any more questions. Thank you!
from sd-dino.
Hi, thank you for your interest in our project. I'd be happy to clarify the code behavior:
The inference code is designed for a
batch_size
of1
for simplicity, henceN
is always1
, andtensor[0]
is equivalent totensor.squeeze(0)
. This doesn't discard any other samples since there is only one sample in the batch.For PCA implementation, please note that the implementation of the PCA used in our default setting is actually the
co_pca
function in utils_correspondence.py. Thepca_process
function here is retained for completeness but may not be the one used in our default setting.Feel free to ask if you have any more questions. Thank you!
Thank you for your patient explanation, I will continue to study this work carefully.
from sd-dino.
Related Issues (16)
- get_mask cannot return valid mask HOT 3
- Collab Demo HOT 1
- Object Swapping (with refinement process) HOT 2
- how to fix the issue of 'RuntimeError: Panoptic/odise_label_coco_50e.py not available in Model Zoo!' HOT 7
- cannot `get_mask` when I vary the cuda device HOT 3
- ValueError: a must be greater than 0 unless no samples are taken HOT 5
- AttributeError: module 'keras.backend' has no attribute 'is_tensor' HOT 3
- Details about how to extract sd features HOT 1
- Questions about sd features HOT 2
- Installation issues for Mask Former HOT 2
- Result different from demo_vis_features.ipynb HOT 4
- License? HOT 1
- The image size for extracting the Dinov2-pretrained-model HOT 2
- Establish environment HOT 3
- Model parameter mismatch 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 sd-dino.