Comments (6)
xperzy
commented on May 26, 2024
是从0开始训练还是加载预训练模型？ ViT模型的尺寸是多少？ ResNet的尺寸是多少？
目前ViT的从0初始化还没有更新，我这边尽快更新下，应该会有帮助
from paddlevit.
xperzy
commented on May 26, 2024
ViT code 已经更新，建议尝试新版本的代码开展实验。
from paddlevit.
Q-amazing
commented on May 26, 2024
好的，收到
from paddlevit.
Q-amazing
commented on May 26, 2024
我是加载了预训练模型，ViT尺寸是patch16_384，ResNet是50_vd.我调整lr=0.0001，batch_size=32，10轮精度就可以达到0.8以上。
from paddlevit.
xperzy
commented on May 26, 2024
如果加载预训练模型，可能是训练的超参数设置需要进行调整，这个需要根据数据集特点和经验进行了。ViT本身模型较大，如果数据集规模不够，可能会出现较难收敛的情况，ViT比ResNet50要大很多。
from paddlevit.
xperzy
commented on May 26, 2024
Since this is related to hyperparameter tuning, not a bug for the code, I close this issue
from paddlevit.
Related Issues (20)
- 请问，何凯明的Masked Autoencoders Are Scalable Vision Learners这篇论文有复现嘛？ HOT 1
- 请问有提供模型训练的日志吗？ HOT 4
- cswin_large_224 pretrained 22k model HOT 4
- t2t利用paddlelite进行pto可以导出定点模型，但评测时报错 HOT 5
- 关于mae的预训练模型是否包含decoder部分 HOT 1
- 说明文档在数据准备阶段的Bug HOT 1
- TopFormer预测精度
- 如何计算VIT模型的Flops ? HOT 1
- 求train_list.txt, val_list.txt HOT 4
- 图片的patch问题
- head_dim
- MobileFormer的预训练权重
- MobileFormer
- ViT pretrained weight with MAE
- 请问vit-base-patch16-224的模型是仅通过仓库训练脚本得到的吗？
- MixSoftmaxCrossEntropyLoss 与MultiCrossEntropyLoss
- 挺好的一个项目，不更新维护了？？ HOT 1
- Hey , I am trying to run your for for the Trans2seg paper, but continously getting this error
- TopFormer implementation differs from original reference implementation
- Cannot get Image Segmentation training to work with custom 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 paddlevit.