Comments (7)
command i used is:
python3 demo.py --config config/fashion-256.yaml --driving_video '11.mp4' --source_image '22.png' --checkpoint 'fashion.pth.tar' --relative --adapt_scale
from first-order-model.
Most likely you have wrong version of pytorch. You need torch==1.0.0
from first-order-model.
Hi. @AliaksandrSiarohin would you mind explaining this "bilinear warping" issue that occurs after pytorch 1.0.0 in detail? And in which part of the code does this issue occurs?
from first-order-model.
Hi,
The problem occurs only in training, at some point model start to diverge and produce some bad solutions. I've tried it with pytroch 1.1, maybe in later versions 1.3, 1.4 it does not occur.
Through I don't have time to investigate it deeply, I belive that the problem is in bilinear warping (
first-order-model/modules/generator.py
Line 57 in 720bdd8
Also, at a test time there are no problems.
from first-order-model.
Thank you for your answer, @AliaksandrSiarohin . I tested this issue with versions 1.2, 1.3 and 1.4, and they all ended in vanishing gradients, but version 1.0.1 works. So I believe that some code change between 1.0.1 and 1.1 was the problem, yet on the update notes there wasn't a significant change on torch.nn.functional.
from first-order-model.
Dear @yj7082126 thank you for letting me know,
The reason, I believe it is in grid_sample because in my other project I meet the same problem when I add a grid_sample with PyTorch 1.1. Without it everything was fine.
I'm not familiar with a PyTorch code base, so it is hard to for me to understand what really changed.
Maybe when I have more time, I will try to remove this grid_sample and try different modes of it.
Anyway thank you for your investigation and for letting me know.
from first-order-model.
Thanks!
from first-order-model.
Related Issues (20)
- Can't use an own video for colab demo HOT 6
- 把first order motion整合到现有框架里 HOT 1
- issue on requirement.txt HOT 1
- out = torch.cat([out, skip], dim=1)
- RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 28 but got size 29 for tensor number 1 in the list. HOT 4
- architecture
- Training doesn't work on custom datasets HOT 12
- model_state_dict and other details
- onxx
- About evaluation
- The model of fashion.pth.tar can not down,because it is error. HOT 1
- real time use
- Software developer
- Retraining 512x512 with 68 keypoints,then retraining 512x512 with dlib 68 keypoints detector HOT 2
- Datasets and contact details
- Cannot install correctly, What do i have to do?
- where is the checkpoint downloaded?
- Cita dgt
- Display of key points HOT 1
- Hi
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 first-order-model.