Comments (4)
Hi @fighting-liu ,
Actually that is my own decision. The original faster rcnn with ResNet cannot insert RPN after res5c because of ROIPooling. But in R-FCN we can do that, and it may look a little bit strange if we make these two parts derive from different layers, so I decided to make them both on top of res5c. And I don't think it will affect final results much, you can try it by yourself :).
from py-r-fcn.
Dear Orpine,
I am using the res5c too, and I find that if you use res5c, this happed:
Now I am training the 4th R-FCN stage (totally 4 stage, with OHEM, 229 category), and
I met a situation that the highest training accuracy(0.949) happened in Iteration 0 (that means just
use the stage 2' model). And after training several iteration(max 110000 as the author set), the final accuray is still lower than Iteration 0.
I feel confuse that Why this happens..., if this always happens, we even do not need the last training stage..., this problem bother me a lot......, help..
I try 3 kind of base learning rate: 0.01, 0.001, 0.0001. the situation I mentioned just now is almost same. just like this:
------------------------- Iteration 0 -------------------------
Training : # accuracy 0.949, loss (cls 0.124, reg 0.243)
Testing : accuracy 0.926, loss (cls 0.201, reg 0.223)
------------------------- Iteration 2000 -------------------------
Training : accuracy 0.938, loss (cls 0.148, reg 0.0596)
Testing : accuracy 0.927, loss (cls 0.2, reg 0.0525)
------------------------- Iteration 4000 -------------------------
Training : accuracy 0.938, loss (cls 0.147, reg 0.0418)
Testing : accuracy 0.927, loss (cls 0.199, reg 0.0504)
------------------------- Iteration 6000 -------------------------
Training : accuracy 0.94, loss (cls 0.144, reg 0.0399)
Testing : accuracy 0.927, loss (cls 0.198, reg 0.0497)
.....
.....
------------------------- Iteration 98000 -------------------------
Training : accuracy 0.943, loss (cls 0.135, reg 0.0315)
Testing : accuracy 0.929, loss (cls 0.193, reg 0.0431)
------------------------- Iteration 100000 -------------------------
Training : accuracy 0.943, loss (cls 0.137, reg 0.0317)
Testing : accuracy 0.929, loss (cls 0.193, reg 0.0431)
------------------------- Iteration 102000 -------------------------
Training : # accuracy 0.943, loss (cls 0.134, reg 0.0317)
Testing : accuracy 0.929, loss (cls 0.193, reg 0.0429)
....
....
And even worse, when testing the image, the proposals I get with RFCN is bad than faster-rcnn(ZF)...., I do not know why?
from py-r-fcn.
Hi @xiaoxiongli , I see you post this in the original R-FCN repo too, and the reason is that the iteration 0 info is useless. It just run 1 iteration, which means it just use 2 images(ims_per_batch=2 if you didn't change it). So the iteration 0's training log is inaccurate(Note that validation loss is accurate) . That's no problem, we can see that the loss decreased indeed.
And it is possible that stage-2 model achieves better result than stage-4 model, because stage-2 model didn't share weights, the RPN you used to produce rois has different weights with R-FCN, which means you introduce more parameters.
I don't understand your last statement, I think R-FCN doesn't produce region proposals, you mean in 4-step training, RPN with R-FCN(ResNet) gives worse region proposals than RPN with fast-rcnn(ZF)?
from py-r-fcn.
Dear @orpine :
thank you for your reply.
Yes, in 4 step training, in my experiment, it seems that RPN with R-FCN(ResNet101) gives worse region proposals than RPN with fast-rcnn(ZF). as I mentioned just now, I am using the res5c which means I share the weight from beginning of the ResNet101 to res5c(including res5c).
I've send a email to you.
from py-r-fcn.
Related Issues (20)
- how to solve the lib reimplement for minibatch size >1 error?
- error use caffe-Microsoft
- I changed it to a single category detection and the loss become NONE in train time after 1000 iter
- about lib/fast_rcnn/train.py
- about multi-scale traing/testing
- ValueError: total size of new array must be unchanged
- Is the backbone network never fine-tuned during training? HOT 1
- Why BN/Scale layers are not included in fine-tune?
- Issue with building microsoft caffe
- a implementation of light head rcnn by modifying R-FCN, low mAP
- train ResNet-50 Alternating training Erroe HOT 3
- when i train rfcn_end2end,there is an error in proposal_target_layer.py
- eltwise_layer.cpp:34 check failed: bottom[i]->shape() == bottom[0]->shape(). error
- undefined reference to symbol 'cudaSetDevice'
- About depth of RoI-wise subnetwork
- How to set iterations when training with rfcn_alt_opt_5stage_ohem
- How to deal with gt_boxes zero sample?>
- Could you give me some hints to fix this issue? Thanks a lot!
- question
- Message type "caffe.LayerParameter" has no field named "psroi_pooling_param".
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 py-r-fcn.