Comments (5)
Hi @ChloeWongxt ,
Please tell us what do you mean by "can't work". Is there any error raised during pretraining? For example, reducing the batch size will only work if it's an OOM error on GPU. If it's an OOM error on CPU, decreasing the num_workers
argument might be a better way to save memory for the dataset loader.
Our pretraining requires a lot of computation CPU resources for matrix decomposition and it took 1 day on our 56-core Xeon(R) CPU E5-2680 v4 @ 2.40GHz so please expect the running time to be long. However, the experiments should be run without any errors with proper configuration. Please paste the specific error/reason preventing the experiments running here and we can see how to solve it.
from gcc.
Our pretraining requires a lot of computation CPU resources for matrix decomposition and it took 1 day on our 56-core
Thanks for your reply!
There isn't any error when i run with the code.
But when i execute the following code, my computer crashed soon.
bash scripts/pretrain.sh 0 --batch-size 16 --num-workers 6 --num-copies 3 --num-samples 200 --epochs 10
The mouse didn't move either. I had to reboot to get it back to normal use.
But I can`t get the result of pre-traing.
from gcc.
Hi @ChloeWongxt ,
Thanks for your feedback. I apologize for the problem caused. It must be frustrating to see the computer crash every time you run the code. I suggest that you try the most low profile setting with:
bash scripts/pretrain.sh 0 --num-workers 1 --num-copies 1
This should consume minimum CPU and RAM on your machine. If this fails, I'm sorry that it's not possible to run pretraining on your machine. However, you can still download our pretrained models and evaluate it on downstream tasks https://github.com/THUDM/GCC/blob/master/GETTING_STARTED.md#download-pretrained-models.
from gcc.
bash scripts/pretrain.sh 0 --num-workers 1 --num-copies 1
Hi @qibinc
Thanks for your patient and detailed rely!
I will try again.
from gcc.
Hi @ChloeWongxt ,
I hope you're doing well. I will close this issue as it seems to be solved. If you meet any other issues on this topic, please feel free to reopen it.
from gcc.
Related Issues (20)
- it seems dgl-0.4.1 cannot work properly HOT 1
- How to make data?
- Running experiments completely on CPU HOT 1
- An error when finetuning on graph classification dataset HOT 3
- Questions about pretraining subgraphs
- Possibly redundant BatchNorm layer? HOT 1
- Can't do node_classification tasks on panther datasets HOT 1
- torch.util.data.IterableDataset HOT 1
- About downstream datasets HOT 2
- When I run the algorithm get an error: "OSError: libcudart.so.10.0: cannot open shared object file: No such file or directory" HOT 3
- finetune HOT 2
- x2dgl.py
- kdd17数据集中的.txt.lpm.lscc
- Please help resolve the problem when the code was running on CUDA11.1 , DGL 0.7, HOT 1
- Regarding the choice of subgraph enhancement method.
- how to unzip small.bin HOT 1
- no edge label for the datasets?
- In generating phase, the necessarity of increasing batch size to the length of dataset. HOT 3
- an error when running x2dgl.py
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 gcc.