Comments (2)
zgcr
commented on May 13, 2024
您好，我想请教一下，为什么咱们自己训练下的权重和pytorch官方给出的预训练权重会相差很大。原本pytorch官方的预训练参数我能到0.616.现在拿咱们这个模型训出来的预训练参数性能只能到0.499. 我是哪一步出错了吗。因为我这个还挺依赖预训练参数。
你好，信息不足，我这边无法判断。我只能确定本库训练的resnet50在ImageNet上的性能。请列出更多详细信息，比如你的下游任务是什么，具体实验设置等等。
from simpleaicv_pytorch_training_examples.
zgcr
commented on May 13, 2024
您好，我想请教一下，为什么咱们自己训练下的权重和pytorch官方给出的预训练权重会相差很大。原本pytorch官方的预训练参数我能到0.616.现在拿咱们这个模型训出来的预训练参数性能只能到0.499. 我是哪一步出错了吗。因为我这个还挺依赖预训练参数。
你好，还有一种情况，你是不是直接拿官方的resnet50定义类去加载我的权重和官方权重了？我这个库的resnet类和官方resnet类虽然网络结构全部一样，但是具体到每层的名字并不一样，直接加载我的权重必定会有部分层权重不能正确加载，甚至有可能所有层的权重都没有加载进去。
from simpleaicv_pytorch_training_examples.
Related Issues (20)
- 训centernet耗时特别长 HOT 1
- RegNet的ColorJitter与原文的PCA-ColorJitter有区别 HOT 1
- How to set num_workers? HOT 1
- pretrained问题 HOT 1
- reg_head in RetinaNet HOT 1
- train.sh HOT 1
- train on RetinaNet HOT 4
- 训练问题 HOT 5
- 多机多卡训练存在很多很多很多问题 HOT 1
- knowledge distillation training seems broken HOT 4
- retinanet训练问题 HOT 7
- yolox backbone error HOT 1
- Could you plz upload the well-trained model HOT 24
- 使用imagenet训练resnet50读取数据有问题，想请教您 HOT 37
- Why do you know that the precision of my cifar100 is higher than the data in the form HOT 2
- 定义模型 HOT 11
- window下clone不了 HOT 1
- about celeba-hq datasets HOT 4
- How to train the Imagnet (which has 300million images) in local machine? HOT 4
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 simpleaicv_pytorch_training_examples.