Comments (5)
daa233
commented on June 12, 2024
你用的什么显卡呀？看上去就是显存不够了
from generative-inpainting-pytorch.
01SHENyankun
commented on June 12, 2024
NVIDIA GeForce GTX 1650
from generative-inpainting-pytorch.
01SHENyankun
commented on June 12, 2024
这种问题有其他解决办法吗
from generative-inpainting-pytorch.
daa233
commented on June 12, 2024
看上去总显存是4G，可以试试 batch_size 1 能不能跑起来。如果能跑起来，就可以用小 batch size 跑。
from generative-inpainting-pytorch.
01SHENyankun
commented on June 12, 2024
不知道是不是我代码写的不对，我是这么写的batch_size = int(real_image.size(0)/16),我试了试2，4，8，32，结果又报错了，说要解压的值太多
from generative-inpainting-pytorch.
Related Issues (20)
- What are the pmconv and allconv layers? HOT 1
- question about CA details HOT 2
- 程序运营问题 HOT 5
- Misalignment with TensorFlow weights HOT 3
- problem with the resulting image HOT 2
- About the function “local_patch(x, bbox_list)” in tools.py HOT 1
- 程序问题 HOT 7
- Mask processing method in ContextualAttention HOT 1
- class Contextual Attention F.conv_transpose2d problem
- TypeError: load() missing 1 required positional argument: 'Loader' HOT 3
- Runtimerror:RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [65536, 1]], which is output 0 of AsStridedBackward0, is at version 6; expected version 5 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True). HOT 2
- validation problem HOT 1
- 关于网络层输出维度不一致
- Train failure with Imagenet HOT 1
- running on another dataset HOT 1
- New easy to use inpanting method with transformers
- Use multiple mask per image HOT 4
- DeepFill v2 Pytorch
- About Mask
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 generative-inpainting-pytorch.