Comments (15)
Try reducing the learning rate? The oscillations in that graph look fairly large. Although if you are using the default learning rate then this is unusual that you should need to change it. Also, make sure that all convolutional layers are fixed (e.g. in both streams of the network).
from goturn.
yet, i only use your code and prototxt( run the train.cpp, keep params of solver.prototxt and tracker.prototxt) to re-train the network, i don't change anymore. the convolutional layer is from CaffeNet, and lr_mult is set 0 no change.
from goturn.
-
I use the pre-trained CaffeNet architecture, which is available from Caffe:
http://caffe.berkeleyvision.org/model_zoo.html -
I think it probably will - if you do this then I recommend using a much smaller architecture.
-
As mentioned above, I do not pre-train the convolutional layers myself but I take the layers pre-trained from Caffe. The two sets of convolutional layers have identical weights.
from goturn.
@davheld I according to your code(tracker.prototxt and solver.prototxt ,iteration 500000) and use the train.cpp to train the network use dataset(2014_DET and ALOV300+), the train loss value is not convergent, and oscillation between on 20 ~ 50 finally.so that have a very pool tracking performance. Can you give me some advise? Thks
from goturn.
It sounds like you are overfitting. Just to be sure - I don't train the conv layers at all, those are pre-trained using CaffeNet.
from goturn.
How do you create the pre-trained network?
from goturn.
the pretrian param from your offer address http://cs.stanford.edu/people/davheld/public/GOTURN/weights_init/tracker_init.caffemodel, i dont change the prototxt, i only want to run train.cpp code to get tracker_iter_500000.caffemodel, then can test the tracker
from goturn.
That's odd, not sure.
from goturn.
I have the same problem, changing val_ratio from 0.2 to 0 in "loader/loader_alov.cpp" may help, but still , model trained by myself doesn't perform as good as pre-train model.
from goturn.
not convergent? oscillation?
from goturn.
The oscillation is normal and simply occurs because the training evaluation is occurring on mini-batches which are randomly sampled at each iteration. However, the numbers that you listed seem lower than what I remember so I believe that you are overfitting, although I am not sure why.
from goturn.
train loss is like this , range from 20 to 90 @OuYag
from goturn.
@OuYag your words"lr_mult is set 0 no change." I don't think it is right, lr_mult set to 0 means no learning rate.
Caffe says that we will set the weight learning rate to be the same as the learning rate given by the solver during runtime
from goturn.
@Jiangfeng-Xiong @OuYag do you solve the issue? I have the same problem, the test loss value is between 10 and 20. I guess it is overfitting, however changing lr or batchsize cannot reduce losses
from goturn.
Hi, I want to know how to evaluate your performance?
from goturn.
Related Issues (20)
- Make error HOT 1
- Attempting to use an MPI routine before initializing MPI HOT 1
- Segmentation fault HOT 3
- stuck with basic issue HOT 1
- The Annotation cannot be loaded
- Understanding the ground truth HOT 1
- integrate GOTURN in the VOT toolkit
- How to deal with error accumulation?
- train without init model?
- Train on Images Only HOT 1
- How to combine GOTURN with another online algorithm?
- Why didn't my loss drop in training?
- 26048 Segmentation fault (core dumped) HOT 1
- Run tracker on single video file
- ‘caffe::Net’ is not a template HOT 3
- undefined reference
- location of annotation in alov300++ dataset is incorrect
- What is the performance for tiny moving objects?
- Segmentation fault on running the tracker test
- The link to pretrained tracker model is invalid. HOT 2
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 goturn.