Comments (14)
you have bug in test code,
i think you havenot restore the rois.
i do this in
Line 292 in 2f3e5c3
rgb's faster rcnn do this in:
https://github.com/rbgirshick/py-faster-rcnn/blob/4e199d792f625cf712ca9b9a16278bafe0806201/lib/fast_rcnn/train.py#L65
from fpn.
@unsky Solved! Amazing result! Thanks for your help!
from fpn.
@liuliu66 Hello, I got a problem same as you. Can you show me the detail that you solved the problem? I still don't know how to fix it. Thanks!
from fpn.
@gk616828144 Hello, my problem is duo to run a wrong sh file so I just check the test.sh and change the model path to my trained model path and the problem is solved. I think if you could run the code on your dataset and got seemly correct loss you could get correct caffemodel file. You can check test.sh and test_mergercnn.sh carefully to solve it.
from fpn.
I have changed the parameters in train.prototxt with changing 21 to 3 (object + background) and 84 to 12.
cls_score_concat :Top shape:4 3(12)?
error:Creating layer loss_cls
F0118 13:55:03.960583 15560 loss_layer.cpp:19] Check failed: bottom[0]->num() == bottom[1]->num() (4 vs. 1) The data and label should have the same number.
from fpn.
@lixiangamy use fpn-caffe!
from fpn.
What are the differences between fpn-caffe and caffe-fast-rcnn?I used caffe-fast-rcnn
from fpn.
from fpn.
@unsky hello,how to restore the rois? I still don't what to do.When I test imgs,the rois is all the same. I don't know where the error is.
from fpn.
@unsky
虽然@liuliu66的问题是由于file文件导致的,但您指出 "i think you havenot restore the rois."这该如何理解呢?
from fpn.
FPN属于faster rcnn框架发展而来,保留了faster rcnn对于rois的设置,faster rcnn 有一个trick就是对第二阶段的rcnn的rois做了白化处理,这种策略可以加速收敛,当然也需要我们在测试阶段进行一次反白化。
from fpn.
@unsky HI
在FPN的test.py中,在im_detect函数
中,对最终的结果确实多了一个normalize操作,这个操作在py-faster-rcnn中是没有的.
在py-faster-rcnn中的trian.py中,也多了一个normalize操作,这个操作在FPN中是没有的.
这2者之间有关系吗?一个是训练的,一个是测试的.而且,您所谓的反白话又是什么意思??
from fpn.
作者您好, 请问训练集像素大小为100100, 目标大小为4040 ,请问 训练时如何设置anchor大小??
谢谢作者啦
from fpn.
您好,请问为什么我训练自己的模型会怎么慢速度?
前面几百次迭代,每20次只需要 34S 左右, 到了2000次左右时, 每20次需要 5-6分钟 为什么会那么慢????? 我的显卡是 GPU 1080Ti 的 12G运行内存
from fpn.
Related Issues (20)
- 修改了anchor数量之后报错了
- mAP询问
- 训练自己的数据集出现了问题
- Changes to Caffe-FPN HOT 1
- TypeError: slice indices must be integers or None or have an __index__ method HOT 3
- Failed to parce NetParameter file:
- wen
- When I run demo.py :Failed to parce NetParameter file
- ModuleNotFoundError: No module named 'generate_anchors'
- 关于模型中p3__lateral和p4__lateral层的疑问
- need ResNet50.v2.caffemodel HOT 1
- 预训练权重
- can't find FP_Net_end2end_merge_rcnn.sh? HOT 2
- 请问 为什么我的训练自己的模型 时间为什么怎么慢呢? HOT 1
- 无法测试 HOT 2
- 保存检测框的结果要怎么修改代码?
- how to continue train?
- 如何进行多尺度的训练? HOT 4
- 增大ratios和scale之后,代码哪些地方需要修改?
- 怎样生成log文件 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 fpn.