Comments (5)
Have you solved it?
from dcl.
Have you solved it?
No, but I know the reason.
You can print the Config.cls_2 and Config.cls_2xmul and you will find they both are 'False'. Actually, I think Config.cls_2 is 'True' and Config.cls_2xmul is 'False' because of config.py (line 124 and line 125)
from dcl.
You can use this
parser.add_argument('--cls_mul', dest='cls_mul', action='store_true', default=True)
or use python train.py --data CUB --epoch 360 --backbone resnet50 \ --tb 16 --tnw 16 --vb 512 --vnw 16 \ --lr 0.0008 --lr_step 60 \ --cls_lr_ratio 10 --start_epoch 0 \ --detail training_descibe --size 512 \ --crop 448 --cls_mul --swap_num 7 7
run code.
from dcl.
You can use this
parser.add_argument('--cls_mul', dest='cls_mul', action='store_true', default=True)
or usepython train.py --data CUB --epoch 360 --backbone resnet50 \ --tb 16 --tnw 16 --vb 512 --vnw 16 \ --lr 0.0008 --lr_step 60 \ --cls_lr_ratio 10 --start_epoch 0 \ --detail training_descibe --size 512 \ --crop 448 --cls_mul --swap_num 7 7
run code.
Thank you !!!
from dcl.
can u explain the meaning of cls_2 and cls_mul? thanks!
from dcl.
Related Issues (20)
- how to solve this problem HOT 1
- 如何解决非目标类得分过高
- RuntimeError: cuda runtime error
- Could you provide some suggestion how to compute heat map when inputting destructed image and get recovery heat map?
- About Region Confusion Mechanism HOT 4
- about test.py? HOT 1
- Why did not find the corresponding place of AngleLinear in the paper
- Reproduce the results in the paper HOT 1
- Download correspond dataset to folder 'datasets'
- TypeError: __init__() got an unexpected keyword argument 'unswap'
- size mismatch for classifier_swap.weight: copying a param of torch.Size([12, 2048]) from checkpoint, where the shape is torch.Size([2, 2048]) in current model.
- The name of each loss function does not match the name on the paper.
- About val.txt
- about AIR dataset HOT 1
- How to train in 224 resolution?
- 我想请问在您的代码中loc损失的标签是什么?
- 请问如何在torch1.8 rtx3060下运行,谢谢
- 为什么算loc损失的时候 要算原图和(i,j)的L1损失呢?M(I)(i,j)和真实的(i,j)不是一样的么?
- How to train on my own dataset?
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 dcl.