Comments (2)
Hi, I figured out that it was because of the threshold being set to 0.7 in faster_rcnn/test_net.py
. Changing the threshold to 0 allows me to see lower APs. However, the APs are really low. Here is what I have, using the default training and testing code:
Results:
0.002
0.032
0.003
0.009
0.002
0.002
0.031
0.004
0.004
0.005
0.002
0.007
0.021
0.004
0.044
0.002
0.009
0.003
0.002
0.002
0.010
~~~~~~~~
Here is my train command:
python ./faster_rcnn/train_net.py \
--gpu 0 \
--weights ./data/pretrain_model/Resnet50.npy \
--imdb voc_2007_trainval \
--iters 150000 \
--cfg ./experiments/cfgs/faster_rcnn_end2end_resnet.yml \
--network Resnet50_train \
--set EXP_DIR exp_dir_resnet50
and my test command:
python ./faster_rcnn/test_net.py \
--gpu 0 \
--weights ./output/exp_dir_resnet50/voc_2007_trainval \
--imdb voc_2007_test \
--cfg ./experiments/cfgs/faster_rcnn_end2end_resnet.yml \
--network Resnet50_test
I already ran the test code inside lib/deform_conv_layer
and lib/deform_psroi_pooling_layer
and compare with my installation of MxNet version. The results and gradients are similar (except some small numerical issures, i.e. some entries in the gradient are different by a factor of 1e-6
). So it looks like the libraries are built correctly.
Do you have any suggestion of what could be the issues here? Thank you.
from tf_deformable_net.
Hi, I figured out that it was because of the threshold being set to 0.7 in
faster_rcnn/test_net.py
. Changing the threshold to 0 allows me to see lower APs. However, the APs are really low. Here is what I have, using the default training and testing code:Results: 0.002 0.032 0.003 0.009 0.002 0.002 0.031 0.004 0.004 0.005 0.002 0.007 0.021 0.004 0.044 0.002 0.009 0.003 0.002 0.002 0.010 ~~~~~~~~
Here is my train command:
python ./faster_rcnn/train_net.py \ --gpu 0 \ --weights ./data/pretrain_model/Resnet50.npy \ --imdb voc_2007_trainval \ --iters 150000 \ --cfg ./experiments/cfgs/faster_rcnn_end2end_resnet.yml \ --network Resnet50_train \ --set EXP_DIR exp_dir_resnet50
and my test command:
python ./faster_rcnn/test_net.py \ --gpu 0 \ --weights ./output/exp_dir_resnet50/voc_2007_trainval \ --imdb voc_2007_test \ --cfg ./experiments/cfgs/faster_rcnn_end2end_resnet.yml \ --network Resnet50_test
I already ran the test code inside
lib/deform_conv_layer
andlib/deform_psroi_pooling_layer
and compare with my installation of MxNet version. The results and gradients are similar (except some small numerical issures, i.e. some entries in the gradient are different by a factor of1e-6
). So it looks like the libraries are built correctly.Do you have any suggestion of what could be the issues here? Thank you.
ha
Hi, I figured out that it was because of the threshold being set to 0.7 in
faster_rcnn/test_net.py
. Changing the threshold to 0 allows me to see lower APs. However, the APs are really low. Here is what I have, using the default training and testing code:Results: 0.002 0.032 0.003 0.009 0.002 0.002 0.031 0.004 0.004 0.005 0.002 0.007 0.021 0.004 0.044 0.002 0.009 0.003 0.002 0.002 0.010 ~~~~~~~~
Here is my train command:
python ./faster_rcnn/train_net.py \ --gpu 0 \ --weights ./data/pretrain_model/Resnet50.npy \ --imdb voc_2007_trainval \ --iters 150000 \ --cfg ./experiments/cfgs/faster_rcnn_end2end_resnet.yml \ --network Resnet50_train \ --set EXP_DIR exp_dir_resnet50
and my test command:
python ./faster_rcnn/test_net.py \ --gpu 0 \ --weights ./output/exp_dir_resnet50/voc_2007_trainval \ --imdb voc_2007_test \ --cfg ./experiments/cfgs/faster_rcnn_end2end_resnet.yml \ --network Resnet50_test
I already ran the test code inside
lib/deform_conv_layer
andlib/deform_psroi_pooling_layer
and compare with my installation of MxNet version. The results and gradients are similar (except some small numerical issures, i.e. some entries in the gradient are different by a factor of1e-6
). So it looks like the libraries are built correctly.Do you have any suggestion of what could be the issues here? Thank you.
I got same problem, have you solved it?
from tf_deformable_net.
Related Issues (20)
- Could you upgrade the lib to support tensorflow 1.4, cudnn 6.0 and cuda 8.0?
- any detail result accuracy about your result? HOT 1
- config.py paras problems HOT 1
- training problems HOT 1
- Is it compatible with cuda9.1 and cudnn7? HOT 6
- Batchsize issue HOT 1
- Offsets Subnet Details HOT 3
- Meaning of num_groups in offsets HOT 3
- How to use this on Windows
- Problems in installation HOT 5
- can it be used in g++4.8? HOT 2
- Can we add deformable convolution at different places?
- Compile Error HOT 12
- deform_conv.so: undefined symbol: _ZN10tensorflow8internal21CheckOpMessageBuilder9NewStringB5cxx11Ev HOT 1
- Thoughts on training on Custom data
- Training error while running faster_rcnn/train_net.py HOT 2
- DCN V2
- compile error
- Error when executing command: make
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 tf_deformable_net.