Comments (11)
参考权重摆放的位置,已经将对应的配置文件复制到cfgs.py中。
from r3det_tensorflow.
from r3det_tensorflow.
cd $PATH_ROOT/tools
python test_dota_r3det_ms.py --test_dir='/PATH/TO/IMAGES/'
--gpus=0,1,2,3,4,5,6,7
-ms (multi-scale testing, optional)
-s (visualization, optional)
请仔细看readme,测试集不需要裁剪
from r3det_tensorflow.
测试集没有切分,但是运行test可视化的时候图片的预测框非常多,特别是边缘,感觉是置信度=0.01的预测结果。运行tools/inference.py则会报错 Shape must be rank 0 but is rank 1 for 'cond/cond/Switch'(op:'Switch') with input shapes : [6], [6]. 请问我该如何运行才能得到置信度0.5的可视化demo?
from r3det_tensorflow.
cd $PATH_ROOT/tools
python test_dota_r3det_ms.py --test_dir='/PATH/TO/IMAGES/'
--gpus=0,1,2,3,4,5,6,7
-ms (multi-scale testing, optional)
-s (visualization, optional)
可视化的就加上 -s
from r3det_tensorflow.
用的是ResNet152_v1d 600->MS (+Flip)这个权重,cfg文件也默认是这个我看,但是运行出的图在其他issue也提到了 很多误检特别是边缘,您说用其他权重和版本,我试了下
R3Det* | ResNet101_v1d 600->800
权重也放在对应位置了,cfg也按照对应的文件去覆盖了原cfg文件的内容,运行python test_dota_r3det_ms.py时权重则会指向检测预训练权重的位置,我把权重重命名移到预训练权重后可以运行,但是出来的结果图没有预测结果
from r3det_tensorflow.
权重则会指向检测预训练权重的位置说明你权重没放对位置或者cfgs没有找到对应的。实在不行你训练一下,存一两个权重就大概知道什么逻辑了。
推荐使用yangxue0827/RotationDetection,用法是一样的,提供了很多方法和相应的权重。
from r3det_tensorflow.
你好 找到问题了,您提供的R3Det_Tensorflow/libs/configs/DOTA1.0/r3det/cfgs_res101_dota_r3det_v19.py 里面41行VERSION = 'RetinaNet_DOTA_R3Det_2x_20200628' 应该改成您网盘里面对应的名字,也就是:VERSION = 'RetinaNet_DOTA_R3Det_3x_20200628'
from r3det_tensorflow.
from r3det_tensorflow.
from r3det_tensorflow.
确实有问题,我已经更新了,感谢提醒。
from r3det_tensorflow.
Related Issues (20)
- 使用DOTA_DEVKIT生成数据量的问题. HOT 3
- I have problems training with my own data. HOT 1
- window训练代码和linux训练代码为什么不同? HOT 8
- where should i put DOTA data set???
- Performance issues in libs/networks/efficientnet/utils.py(P2)
- Performance issue in the definition of libs/networks/efficientnet/condconget_condconv_initializer, v/condconv_layers.py(P1) HOT 1
- Performance issue in libs/networks/efficientnet/ (by P3) HOT 1
- Retinanet-H/R with MobilenetV2 backbone train issue
- Tflite conversion issue......
- 请问有测试map的代码吗
- loss nan problem
- 关于复现的问题 HOT 6
- what does "lr schd" mean? HOT 2
- 关于论文中红绿灯检测的是如何训练的呢?我使用Retinanet作为 base model训练出来的效果并不理想 HOT 2
- redundant inference in the sliding window of test_dota HOT 1
- error: command '/usr/bin/gcc' failed with exit code 1 make: *** [Makefile:2:all] 错误 1
- 关于特征图重构的问题
- 没有找到相应文件(Can not find such document)
- 不知道除了什么问题,运行到这里卡住了
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 r3det_tensorflow.