Comments (4)
你是训练的时候修改了网络结构还是什么?按正常流程训练完加载是没问题的,要么就是cfg相应位置没修改
from awesome-backbones.
你是训练的时候修改了网络结构还是什么?按正常流程训练完加载是没问题的,要么就是cfg相应位置没修改
我通过torchvision加载了一个mobilenet_v3_small网络模型,进行torch.load可以正常加载
然后我把它训练一次之后得到的权重文件,在进行如上图一样的加载,就会报错,好像网络结构不一致了。
from awesome-backbones.
你是训练的时候修改了网络结构还是什么?按正常流程训练完加载是没问题的,要么就是cfg相应位置没修改
或者说我经过咱们这个系统训练完的pth文件,应该怎么在别的地方加载呢
from awesome-backbones.
torchvision对应的网络模型键名对不上当然权重无法映射,得在该项目下训才可以
from awesome-backbones.
Related Issues (20)
- 权重大小不匹配 HOT 2
- evaluation 进行模型评估时,数据集从何而来 HOT 2
- 该程序想要在pycharm中运行该怎么使用 HOT 1
- 如果用mvit,t2t_vit,visiontransformer三个算法分别得到三个模型,如何用adaboost将他们集成呢,这是可行的吗
- upup,为啥只有训练loss和验证acc HOT 4
- 数据集问题 HOT 1
- 能否批量输出类激活图 HOT 2
- 是否支持训练视频分类?
- 怎么用训练好的模型批量预测呀 HOT 4
- 作者您好,请教关于mobilenetv3 small的输出维度问题 HOT 1
- Loss损失函数问题 HOT 1
- opencv_python、opencv_contrib_python、opencv-python-headless 的版本用的多少啊,总是说我的版本不匹配 HOT 1
- 1.电脑有两个GPU 0和1,如何改代码使它使用GPU1呀。2.CUDA out of memory这个问题是因为什么呀 HOT 1
- 请问这个报错:AttributeError: 'EfficientFormerClsHead' object has no attribute 'post_process',没有post_process()方法? HOT 6
- 怎么导出.wts HOT 1
- 1
- 怎么改变批量预测的结果字体的大小 HOT 7
- 为什么训练时,精确度能有90%多,但模型评估时,预测结果准确率很低,甚至有时会出现预测结果全为一类(我预测的是二分类) HOT 1
- 后续会加入一些新的模型吗比如squeezenet、xception
- 加入新的主干运行后出现Initialize the weights. Traceback (most recent call last): File "tools/train.py", line 171, in <module> main() File "tools/train.py", line 136, in main max_iters = data_cfg.get('train').get('epoches')*len(train_loader), TypeError: unsupported operand type(s) for *: 'NoneType' and 'int'的问题怎么解决 HOT 1
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 awesome-backbones.