Comments (6)
You can reduce the batch size (N_rand) or the chunk size in the config file to fit in a GPU with small memory.
from dsnerf.
I found that after completing the first 10,000 training sessions, the mp4 video will be rendered first, and then the training will be continued.
My problem is that there is not enough memory when rendering to generate mp4 video (eg: fern_2v_spiral_010000_disp.mp4). Is this step of generating video necessary? Can I complete the training first, and then render (--render_only)
from dsnerf.
I found that after completing the first 10,000 training sessions, the mp4 video will be rendered first, and then the training will be continued. My problem is that there is not enough memory when rendering to generate mp4 video (eg: fern_2v_spiral_010000_disp.mp4). Is this step of generating video necessary? Can I complete the training first, and then render (--render_only)
@jmwang0117 Have you fixed that problem?
from dsnerf.
I found that after completing the first 10,000 training sessions, the mp4 video will be rendered first, and then the training will be continued. My problem is that there is not enough memory when rendering to generate mp4 video (eg: fern_2v_spiral_010000_disp.mp4). Is this step of generating video necessary? Can I complete the training first, and then render (--render_only)
Hi,could I ask what pytorch version you use? Did you modified any code from the original repo?I use the version 1.7.0,but encounterd problem every time I reached to 4999iters
from dsnerf.
I found that after completing the first 10,000 training sessions, the mp4 video will be rendered first, and then the training will be continued. My problem is that there is not enough memory when rendering to generate mp4 video (eg: fern_2v_spiral_010000_disp.mp4). Is this step of generating video necessary? Can I complete the training first, and then render (--render_only)
Hi,could I ask what pytorch version you use? Did you modified any code from the original repo?I use the version 1.7.0,but encounterd problem every time I reached to 4999iters
Block code that generates video
from dsnerf.
I found that after completing the first 10,000 training sessions, the mp4 video will be rendered first, and then the training will be continued. My problem is that there is not enough memory when rendering to generate mp4 video (eg: fern_2v_spiral_010000_disp.mp4). Is this step of generating video necessary? Can I complete the training first, and then render (--render_only)
@jmwang0117 Have you fixed that problem?
Block code that generates video
from dsnerf.
Related Issues (20)
- Do we need to run COLMAP with the exact poses given in the datasets like DTU and Blender HOT 2
- depth = (poses[id_im-1,:3,2].T @ (point3D - poses[id_im-1,:3,3])) * sc ,WHY? HOT 3
- Generate colmap data HOT 5
- Colmap with load_llff function
- weights = np.repeat(depth_gts[i]['error'][:,None,None], 3, axis=2) # N x 1 x 3 KeyError: 'error' HOT 2
- " allow_unreachable=True, accumulate_grad=True) # Calls into the C++ engine to run the backward pass RuntimeError: Function 'PowBackward0' returned nan values in its 0th output" HOT 1
- Questions about rendering the video HOT 1
- run COLMAP with ground truth camera poses on Custom Data
- what does relative loss mean? HOT 1
- chapter 3.2 line 9. taking the re-projected z value? HOT 1
- OOM error HOT 1
- How to partition the DTU dataset? HOT 1
- sigma_ Loss and depth_ Differences in loss HOT 1
- RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! HOT 3
- Hi,I can't run your code because of line 1278, in _save rawmode, mode = _OUTMODES[mode] KeyError: 'F' HOT 2
- configs issue HOT 9
- new experiment by kangle HOT 1
- Is there sometime that sigmaloss may be inf? HOT 1
- 1
- difference of Poses created by colmap and poses created for each dataset
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 dsnerf.