Comments (12)
@unsky Hi, thanks for your work. I have tried training ResNet50 deformable Fast RCNN end2end model on WIDER FACE DataSet, the loss seemed normally converge, but I got nothing when I test my model. Moreover, I have tried training deformable VGG16 on Imagenet, the loss could not even converge. Do you have any idea about this?
Best
from deformable-convnets-caffe.
the setting of batch norm is very very import in detection task,you can refer the setting in my model.
ps:i think there have mang bugs in your test
from deformable-convnets-caffe.
@unsky I don't think I have many bugs in my test, here is my results using your res50 faster rcnn config but replace deformable convolution by normal convolution, trained on WIDER FACE with 120000 iterations.
And all my BatchNorm config in training is like below:
layer {
bottom: "res3a_branch1"
top: "res3a_branch1"
name: "bn3a_branch1"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
param {
lr_mult: 0.0
decay_mult: 0.0
}
param {
lr_mult: 0.0
decay_mult: 0.0
}
param {
lr_mult: 0.0
decay_mult: 0.0
}
}
layer {
bottom: "res3a_branch1"
top: "res3a_branch1"
name: "scale3a_branch1"
type: "Scale"
scale_param {
bias_term: true
}
}
Can you share your deformable resnet50 faster rcnn trained model on PASCAL VOC to help me check my mistakes?
Thank you
from deformable-convnets-caffe.
@RuiminChen
https://github.com/unsky/Deformable-ConvNets-caffe/blob/master/deformable_conv_faster-rcnn/models/pascal_voc/ResNet50/faster_rcnn_end2end/train.prototxt
i think we should fix scale params
from deformable-convnets-caffe.
Hi,@RuiminChen ! Have you solved the problem on VGG16?
from deformable-convnets-caffe.
@lawpdas yes, my results seems normal now on both resnet50 and VGG16
from deformable-convnets-caffe.
@RuiminChen What should I do with VGG16? Can you give me some suggestions?
Thanks!
from deformable-convnets-caffe.
@RuiminChen Could you tell me whether transferring the deformable convolutional network to the VGG 16 network works or not? I'm planing to apply the deformable convolutional network to the visual tracking field and quite curious about the effect of it.
Looking forward to your reply!
from deformable-convnets-caffe.
@RuiminChen Hi ~ I have trained a classification network using deformable ResNet50 and the loss could converge. But when i viewed the offset the model have learned, I found it was very big. It seems like the network dosn't even use these deformable conv layer because the offsets are out of the image boundary..
How do you train the vgg net for ImageNet cls task?
from deformable-convnets-caffe.
@zhanglonghao1992 You may check DCNV2 here https://github.com/msracver/Deformable-ConvNets, They have already solved a possible issue when the sampling location is outside of image boundary
from deformable-convnets-caffe.
@unsky I don't think I have many bugs in my test, here is my results using your res50 faster rcnn config but replace deformable convolution by normal convolution, trained on WIDER FACE with 120000 iterations.
And all my BatchNorm config in training is like below:
layer {
bottom: "res3a_branch1"
top: "res3a_branch1"
name: "bn3a_branch1"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
param {
lr_mult: 0.0
decay_mult: 0.0
}
param {
lr_mult: 0.0
decay_mult: 0.0
}
param {
lr_mult: 0.0
decay_mult: 0.0
}
}layer {
bottom: "res3a_branch1"
top: "res3a_branch1"
name: "scale3a_branch1"
type: "Scale"
scale_param {
bias_term: true
}
}
Can you share your deformable resnet50 faster rcnn trained model on PASCAL VOC to help me check my mistakes?
Thank you
Could you tell me some details about how to solve the problem?
from deformable-convnets-caffe.
Hi, @aresgao @RuiminChen @unsky @lawpdas @haoliyoupai09 , could you tell me if there exist bugs in the code, as in #31 (comment)? Thank you.
from deformable-convnets-caffe.
Related Issues (20)
- the error after make HOT 4
- could you release deformable roipooling HOT 2
- Ask for help ,about the traing of deform HOT 3
- The hyper-parameters for reproduce the deform conv model on VOC
- About example 'mnist' HOT 2
- model share
- ResNet50_dcn_iter_30000.caffemodel
- matcaffe error HOT 7
- caffemodel HOT 2
- train.prototxt
- What's the use of deformable_group? HOT 3
- shape mismatch HOT 1
- Have you ever tried deformable conv on classification network? HOT 2
- Serious problems occurred when training cls network with dcn HOT 2
- Problem about the code. HOT 5
- Use by pycaffe
- 有两个bug
- Does anyone solve the problem of over large offset?
- Shape of bottom[1]
- Can you provide one train.prototxt with deformable ROI pooling?
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 deformable-convnets-caffe.