Comments (7)
valid_paths.json.zip
There you go! The validation is the last 1 percent of the rows (first 99 percent used for training).
P.S. if you want to compare against our model on objaverse dataset, please use 105000.ckpt
instead of 165000.ckpt
as the latter might have been trained on some part of the validation sets unintentionally. As our paper focuses on zero-shot generalization, it didn't really matter but it does when you run in-distribution experiments.
from zero123.
For GSO and RTMV, we render a bunch of views whose camera poses are randomly sampled. We use the first view as input and the following views for evaluation. Since all views are uniformly sampled, the order doesn't make a difference. Same applies for Objaverse but since our paper focuses on zero-shot performance, we did not run evaluation on objaverse which is our training dataset.
from zero123.
Hi @wzic , a few hundreds (or thousands) of our downloaded files are corrupted or didn't render correctly, so I created a valid_paths.json to store the path to valid rendering folders.
from zero123.
Then what's the content in valid_paths.json? Is it a list of the ids of the objects? How about the format?
from zero123.
@wzic From what I can tell it is just a list of the valid object uids in json
from zero123.
@ruoshiliu , it'd be very helpful if you can release the valid_paths.json
file, otherwise, we are not able to know which objects are used for training/validation.
from zero123.
Hi, can you explain in more details how the evaluation is performed? More specifically, how do you choose which image you use as context, and which ones you use for novel view synthesis?
from zero123.
Related Issues (20)
- Zero123 autoregressive generation
- color mesh structure HOT 1
- The dataset file is too large,about 1.5TB, it's hard to download.
- focal length and principal point of the dataset
- Can export the mesh with texture
- getting some cv2 related error HOT 1
- Cant figure out where to put the model
- sd basemodel HOT 1
- UserWarning: ModelCheckpoint(monitor=’val/loss_simple_ema’) not found in the returned metrics HOT 1
- how to create_carvekit_interface without the online access to huggingface?
- Partial dataset HOT 7
- RuntimeError: DataLoader worker (pid(s) 3360242, 3361527, 3362405) exited unexpectedly HOT 4
- test/benchmark on non-object data
- Can we continue training on the basis of 105000.ckpt? HOT 1
- Run time error `python gradio_new.py` HOT 2
- demo is down
- Partial Objaverse dataset for demo HOT 3
- batch size issue when trianing custom dataset HOT 1
- offline rendering or online rendering
- How to change the view of the input picture
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 zero123.