Comments (3)
Please see this thread for layer specific changes: #9
Note that this will not suffice if you are changing anchors as well. Let me know if you are doing that.
To fine tune an existing model, you can replace the ResNet-<50/101>-model.caffemodel that you provide while following training steps.
from py-r-fcn.
@ravikantb What are some heuristics for fine tuning the RFCN network when training on own dataset? E.g. on a moderate number of classes lower than PASCAL_VOC but where classes are harder than those on PASCAL_VOC (cars, ...)
from py-r-fcn.
@
I have already fined tune resnet101_rfcn_final.caffemodel model, it got 95% accuracy in training. But in demo_rfcn.py, I test my image, the predicted boxes were inaccurate. I do not know why?
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.