Comments (4)
Hi, sorry but your questions is really confusing:
- I don't get the question. There is no L1 in train mode.
- What is 768?
- Could you provide example?
- Depends on what objects will be in the new dataset.
from articulated-animation.
- I used the reconstruction results of train mode to calculate the L1 loss and the reconstruction results of avd mode are almost the same, so I think avd mode is not effective
- I cut TED dataset with 768*768 size
- The new dataset is based on half-speaker video objects. Some videos of the new dataset are below,The new data sets are highly heterogeneous and diverse
https://user-images.githubusercontent.com/28126038/182800076-b9e4dea5-d927-41cd-ab7d-038e2cfccbf3.mp4
https://user-images.githubusercontent.com/28126038/182800140-632904d1-27e7-4a4a-9ec2-142fc59e01b5.mp4
https://user-images.githubusercontent.com/28126038/182800340-c7f54217-72a0-4a01-99d4-6cd7c4ec64e9.mp4
3.train mode visualization Results
0gks6ceq4eQ.004737.004870.mp4.mp4
avd mode visualization Results
0gks6ceq4eQ.004737.004870.mp4.mp4
Is it convenient for you to provide the training log? I want to compare it with my log. Thank you. Is there anything unclear
from articulated-animation.
- Reconstruction does not make sense for avd, since it specifically designed for cross identity, where the shapes of the objects could be different.
- There are no explicit handling of parts that is not visible most of the time, I guess you will have to device some way of handling that.
- I can't see what bothers you in optical flow map.
- Unfortunately I don't have logs anymore.
from articulated-animation.
- Reconstruction does not make sense for avd, since it specifically designed for cross identity, where the shapes of the objects could be different.
- There are no explicit handling of parts that is not visible most of the time, I guess you will have to device some way of handling that.
- I can't see what bothers you in optical flow map.
- Unfortunately I don't have logs anymore.
Thank you for your prompt reply.
-
Since there is no problem with the optical flow diagram, does it mean that there will be a problem that the details of the reconstruction are not clear? Is the reason that the reconstruction details are not clear is that the generator is not strong enough or the information of the optical flow diagram is not fully utilized?
-
Do you think it is OK for me to use half-speaker videos with complex background and inconsistent height in my self-built data set? It seems to me that Loss is decreasing rapidly at present, and then it will not decrease
VIDEzO9Daec770Ndf6uLP9uc220323.057018.057137.mp4.mp4
https://user-images.githubusercontent.com/28126038/182990785-43862275-00db-4a46-a569-6dc1489180b4.mp4
Uploading 20200507094714_11_aC9no_1080p#008375#008417.mp4.mp4…
VIDEST94vUrlZI7XD2po9et1220128.040894.041054.mp4.mp4
20180614112218_419_zwosJ_1080p.011847.011863.mp4.mp4
VIDEzO9Daec770Ndf6uLP9uc220323.024783.024804.mp4.mp4
from articulated-animation.
Related Issues (20)
- Is there a way to keep the audio?
- error when training avd with videos HOT 1
- What version of CUDA, cuDNN are you using? HOT 6
- produce smooth video results
- Some questions about Teddataset HOT 1
- your colab brings a ton of errors.
- Why do your images work pretty well but my images make the result very bad
- When training, does the input image pixel size need to be consistent?
- What source images do you use to compute IoU for co-part segmentation (Section 4.5) in the paper?
- from skimage.draw import circle ImportError: cannot import name 'circle' from 'skimage.draw' (/home/onur/.local/lib/python3.9/site-packages/skimage/draw/__init__.py) HOT 4
- Discriminator module
- Git LFS quota limit HOT 2
- Dataset request
- RuntimeError: Error(s) in loading state_dict for Generator: size mismatch for pixelwise_flow_predictor.hourglass.encoder.down_blocks.0.conv.weight: copying a param with shape torch.Size([128, 44, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 84, 3, 3]). HOT 4
- How to get the ted-youtube384.pth ? HOT 1
- Disentanglement is not good
- Regarding the start and End time of the videos HOT 1
- Not able to fine tune ted-youtube384.pth model. HOT 9
- what should i do to test the cloth swap
- youtube-dl problem 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 articulated-animation.