Light

Train problem about restormer HOT 7 CLOSED

leftthomas commented on June 16, 2024

Train problem

from restormer.

Comments (7)

leftthomas commented on June 16, 2024

@zhangbaijin you have no images in that path.

from restormer.

zhangbaijin commented on June 16, 2024

你好，我在训练当中遇到out of memory的问题，在A100 80G的显卡上训练，不知道是哪里出问题了？

from restormer.

zhangbaijin commented on June 16, 2024

Traceback (most recent call last):
  File "main.py", line 84, in <module>
    out = model(rain)
  File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/root/autodl-tmp/Restormer-master/model.py", line 115, in forward
    out_enc1 = self.encoders[0](fo)
  File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/container.py", line 204, in forward
    input = module(input)
  File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/root/autodl-tmp/Restormer-master/model.py", line 59, in forward
    x = x + self.ffn(self.norm2(x.reshape(b, c, -1).transpose(-2, -1).contiguous()).transpose(-2, -1)
  File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/root/autodl-tmp/Restormer-master/model.py", line 42, in forward
    x = self.project_out(F.gelu(x1) * x2)

from restormer.

leftthomas commented on June 16, 2024

@zhangbaijin this code requires 8xV100, or you should reduce size

from restormer.

zhangbaijin commented on June 16, 2024

read me不是说在一张A5000训练的吗。。。可能是我理解错了

from restormer.

zhangbaijin commented on June 16, 2024

我把数据集reduce到了384X384，8张3090的显卡，依然是报CUDA的错？

from restormer.

zhangbaijin commented on June 16, 2024

我把batchsize调到了
parser.add_argument('--batch_size', nargs='+', type=int, default=[32,20,16,8,4,4], help='batch size of loading images for progressive learning') parser.add_argument('--patch_size', nargs='+', type=int, default=[64,80,96,128,160,192], help='patch size of each image for progressive learning') parser.add_argument('--lr', type=float, default=0.0003, help='initial learning rate') parser.add_argument('--milestone', nargs='+', type=int, default=[9200,15600,20400,24000,27600], help='when to change patch size and batch size')
目前可以训练，不知道效果怎么样

from restormer.

Related Issues (5)

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.