Comments (8)
littletomatodonkey
commented on May 23, 2024
您好，这个问题已经修复，麻烦获取下最新代码，您也可以参考这个PR： #147
from paddleclas.
barry2025
commented on May 23, 2024
多谢！更新paddle版本后已解决。现在是出现如下错误：
看着跟算loss有关，请问下是类别配置的问题么
from paddleclas.
littletomatodonkey
commented on May 23, 2024
您好，看着应该是某个变量的stop_gradient应该设置为true，方便提供下您的训练脚本吗？我这边复现看下
from paddleclas.
barry2025
commented on May 23, 2024
训练脚本：https://bj.bcebos.com/v1/mct-imagedb/tangxin-bos/tmp/prob/train.sh
yaml文件：https://bj.bcebos.com/v1/mct-imagedb/tangxin-bos/tmp/prob/ResNet50_vd.yaml
构建数据集后，修改yaml文件，模型结构方面没有修改
目前paddleclas版本：
麻烦帮忙看下
from paddleclas.
littletomatodonkey
commented on May 23, 2024
您好，您可以切换到Paddle1.8以上版本，也可以参考 #153 去获取下最新代码。
from paddleclas.
barry2025
commented on May 23, 2024
请问下您这边的建议呢，跑paddlelclas库是用paddle18比较好？(我这边目前跑paddledection用paddle18，跑其中一个yml时，会有一个element op相关的错误)
from paddleclas.
littletomatodonkey
commented on May 23, 2024
您可以修改代码之后，使用paddle1.7或者2.0
from paddleclas.
barry2025
commented on May 23, 2024
好的，非常感谢！修改后可以跑起来了
from paddleclas.
Related Issues (20)
- 使用PPLCNetV2_base_ShiTu模型，在GPU上运行加速效果不明显 HOT 1
- PaddleClas,图像识别部署，根据2.5文档服务化部署预测过程中出现报错 HOT 4
- 一张图片中两行文字发生了折叠，如果有文字发生折叠的图片和文字未发生折叠的图片，用哪一个分类模型效果会好一些？ HOT 3
- PaddleClas 如何实现模型在train 以及 infer 的时候使用不同分支的forword HOT 1
- KeyError: 'save_infer_model/scale_0.tmp_1.lod' HOT 1
- PPLCNetV2_base_ShiTu模型增加图片的分辨率跟输出的维数会增加检索精度吗？ HOT 1
- Direct prediction API HOT 1
- 关于paddleClas和paddlepaddle版本的问题 HOT 5
- release/2.5 ModuleNotFoundError: No module named 'ppcls' HOT 3
- paddleclas.PaddleClas使用inference_model_dir指定模型PULC模型识别有误 HOT 1
- 想要做一个文物拍照识别的课题研究，PP-ShituV2是否适合？ HOT 2
- pp-shituv2 使用paddleserving部署后启动服务运行python3.7 pipeline_http_client.py报/home/aistudio/PaddleClas/deploy/paddleserving/recognition {'err_no': 8, 'err_msg': "(data_id=0 log_id=0) [det|0] Failed to postprocess: 'scale_factor.lod'", 'key': [], 'value': [], 'tensors': []} HOT 2
- 训练时报错 OSError: (External) CUDA error(719), unspecified launch failure. HOT 7
- 怎么训练出不带reshape2算子的general_PPLCNetV2_base模型？ HOT 2
- 训练报错 HOT 1
- 首次接触paddle，我想在win10上部署，应该看哪个教程 HOT 2
- ERROR: Unexpected segmentation fault encountered in DataLoader workers.
- 我运行的是PP-ShitV2（PP-ShiTu PC端 demo 快速体验），我想修改代码，使输出结果可以显示三个种类可能性，请问如何修改代码
- ImportError: cannot import name 'ClsPredictor' from 'deploy.python.predict_cls'
- gpu下预测的结果都是正常的，但切换到cpu下预测，结果全是nan
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 paddleclas.