Comments (2)
Disclaimer - Not a CLIPSeg author, just a user.
- The unzipped and structured datasets should be located in ~/datasets/dataset_name/... This will circumvent the functionality to un-tar a complete and already structured dataset from ~/dataset_repository/, although you could use this if you have one.
- I reverse engineered the dataset setup for COCO. Setting up this dataset for training required following these instructions from the hsnet repository:
COCO-20i
Download COCO2014 train/val images and annotations:
wget http://images.cocodataset.org/zips/train2014.zip
wget http://images.cocodataset.org/zips/val2014.zip
wget http://images.cocodataset.org/annotations/annotations_trainval2014.zip
Download COCO2014 train/val annotations from our Google Drive: [train2014.zip], [val2014.zip]. (and locate both train2014/ and val2014/ under annotations/ directory).
Resulting in folder structure:
~/datasets/
├── COCO-20i/
│ ├── annotations/
│ │ ├── train2014/ # (dir.) training masks (from Google Drive)
│ │ ├── val2014/ # (dir.) validation masks (from Google Drive)
│ │ └── ..some json files..
│ ├── train2014/
│ └── val2014/
If you have a dataset that is set up like the COCO one seen above, then you can change the dataset folder name in the 'wrappers' folder in the 'coco_wrapper.py' file to have the code use your custom dataset instead, although this will also require some changes in the way CLIPSeg uses hsnet to index the dataset.
from clipseg.
I think @erkoiv already provided a great answer. The get_from_repository
function is primarily used as an internal tool. In this repository it is sufficient to put the data into ~/datasets/<dataset>/
.
from clipseg.
Related Issues (20)
- Difference in PhraseCut images number HOT 1
- Missing imports in `Tables.ipynb` and `Visual_Feature_Engineering.ipynb` HOT 1
- About zero-shot experiment HOT 1
- Binder demo does not start HOT 2
- How to recognize instances in the image? HOT 1
- The datasets used to train the released model CIDAS/clipseg-rd64-refined HOT 1
- Weights for ViT-B/32 version of CLIPDensePredT HOT 5
- License of model weights HOT 1
- FileNotFoundError: [Errno 2] No such file or directory: './dataset_repository/PhraseCut.tar' HOT 2
- Object Not Present HOT 1
- image with mask prompt for one shot (revisit) HOT 2
- Can you share the LVIS subset? HOT 1
- Quickstart notebook and refined weights HOT 1
- Performance on Pascal-5i one-shot HOT 2
- Clip cannot be used HOT 2
- Predicted mask image has different dimension than input image HOT 1
- Missing __init__.py file causes import errors HOT 1
- Missing datasets.lvis_oneshot3 folder HOT 1
- Missing file category_info.json 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 clipseg.