Comments (2)
Hi, sorry for the late reply. I'll do my best to answer all of your questions, but please let me know if I miss anything.
- Registering a COCO format dataset: Since we're using Detectron2, I recommend checking out the "Use Custom Datasets" tutorial in the Detectron2 documentation for a detailed explanation on how to register custom datasets. You can also follow our approach to registering ImageNet by modifying the "builtin.py" and "builtin_meta.py" files in the "cutler/data/datasets" directory of our GitHub repository.
- Would it be easier to just use the naming convention of imagenet? Yes, it is. But I may recommend you register a new dataset.
- The command to run the merge_jsons.py. Yes, you should use the one that was generated after running the maskcut.py.
- Parameters. 1) The test-dataset should be the entire training set, as we'll be using the model's predictions on the training set as the pseudo-masks for the next stage of self-training. 2) The MODEL.WEIGHTS parameter should point to the checkpoint obtained from the unsupervised model learning stage. 3) OUTPUT_DIR specifies the path where the model predictions will be saved. These predictions will be used as the "ground-truth" for the next stage of self-training. 4) The default name for the model predictions is "coco_instances_results.json", but you can check the files saved under OUTPUT_DIR/inference/ and modify the name accordingly if needed.
- Repeat the self-training process multiple times. If you only care about the final results and not the intermediate ones, the easiest approach is to overwrite the results of the previous runs. This means that you should always use the same file name, such as r1.json or r2.json. However, if you want to keep track of the results from each run, you'll need to register the "new" dataset. The images will be the same as before, but the annotations will be updated for each run. For example, you could name the updated datasets "cutler_imagenet1k_train_r3.json" or "cutler_imagenet1k_train_r4.json".
Hope these answers help.
Best,
XuDong
from cutler.
Closing it now. Please feel free to reopen it if you have further questions.
from cutler.
Related Issues (20)
- Can't download a model from the model zoo. HOT 5
- eigh() got an unexpected keyword argument 'subset_by_index' HOT 2
- backbone change HOT 1
- ModuleNotFoundError: No module named 'third_party' HOT 2
- Can i train a "videocutler"? HOT 5
- Error when running videocutler demo HOT 4
- Set up panoptic/semantic segmentation with cutler HOT 4
- Error with imports when using the notebook demo for maskcut HOT 4
- Can i visualize the synthesis training data? HOT 1
- Compatibility of Cut and Learn (CutLER) Model with Windows HOT 1
- Can Cutler be converted to trt engine file HOT 1
- Colab and huggingface Demo not working HOT 1
- copy_and_paste code error HOT 1
- Can I train a 3090 without affecting the effect? HOT 2
- Setting of VideoCutLER's baseline
- question about customized data training HOT 1
- When I perform self-training I get an error file
- is pre-trained VideoCutLER available?
- Adapting CutLER for other detectors
- cuda
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 cutler.