Comments (15)
Hi @pribadihcr
Your input data with only 1 channel?If so, you should generate 2 channel input data, that 1ch for an image, 2ch for another matched image, like caffe/examples/siamese.
from matchnet.
@zhengxiawu can you please share your solver parameters or loss function? Is the LR the only thing you changed? He used SoftmaxWithLoss here, but actually the paper talkes about Softmax+CrossEntropy, which isn't available in Caffe, since there is only SigmoidCrossEntropy. No idea if that is the problem though. I have the same 0.69 loss.
UPDATE: It turns out it had to do more with the weight initialization than the LR. If u try out some different fillers, it'll work. In my case, it worked with using guassian fillers with 0.1 std on the first conv layers.
from matchnet.
@snailchan , I also have the same problem, have you solved it ?
from matchnet.
@killerjian007 , I stopped here for a long time. If you had a solution, I would appreciate your sharing!
from matchnet.
Hi @snailchan @killerjian007 ,
I got the following error:
I1220 17:46:56.192490 14214 layer_factory.hpp:77] Creating layer pair_data
I1220 17:46:56.195097 14214 net.cpp:106] Creating Layer pair_data
I1220 17:46:56.195261 14214 net.cpp:411] pair_data -> pair_data
I1220 17:46:56.195397 14214 net.cpp:411] pair_data -> sim
I1220 17:46:56.312755 14220 db_leveldb.cpp:18] Opened leveldb /home/rudy/matchnet/data/leveldb/liberty.leveldb
I1220 17:46:56.340694 14214 data_layer.cpp:41] output data size: 64,1,64,64
I1220 17:46:56.347340 14214 net.cpp:150] Setting up pair_data
I1220 17:46:56.347489 14214 net.cpp:157] Top shape: 64 1 64 64 (262144)
I1220 17:46:56.347564 14214 net.cpp:157] Top shape: 64 (64)
I1220 17:46:56.347625 14214 net.cpp:165] Memory required for data: 1048832
I1220 17:46:56.347702 14214 layer_factory.hpp:77] Creating layer slice_pair
I1220 17:46:56.347810 14214 net.cpp:106] Creating Layer slice_pair
I1220 17:46:56.347884 14214 net.cpp:454] slice_pair <- pair_data
I1220 17:46:56.347990 14214 net.cpp:411] slice_pair -> data
I1220 17:46:56.348096 14214 net.cpp:411] slice_pair -> data_p
F1220 17:46:56.348245 14214 slice_layer.cpp:44] Check failed: top.size() <= bottom_slice_axis (2 vs. 1)
*** Check failure stack trace: ***
I used @snailchan matchnet_siamese & solver.prototxt above.
For your help, thank you very much.
from matchnet.
@killerjian007
I generated input data using default matchnet code: generate_patch_db.py.
do, I need generate data using convert_mnist_siamese_data in caffe ?.
from matchnet.
Hi, @killerjian007 , have you solved the problem?
from matchnet.
i have the same problem also. i used my own data to train. maybe the format of training data is wrong??(i am trying to find the error).do you preprocess the training data as the paper??
from matchnet.
@snailchan ,i've been on this experiment for a long long time,and my loss was still about 0.69,how can i know the way the author train this network
from matchnet.
@LeonSCZ i had used matconvnet to do the network ,and found that the learning rate should be less than 0.00005, you can try it in caffe
from matchnet.
@mkaraki48 Do you have solve the problem?
from matchnet.
@pribadihcr How did you solve the error?
from matchnet.
hi,
after training,
how can i convert the caffemodel/solverstate file to .pb file for pycaffe invoking?
is there any tools for the convertion from solverstate to .pb?
from matchnet.
@mkaraki48 Could you please share your solver.prototxt that you have used to get reasonable response from training the network? I still get the 0.69 loss the entire training time even with the parameters that you have shared in your update. Thanks a lot!
from matchnet.
Can you please tell me how to train this model on my dataset
from matchnet.
Related Issues (13)
- Issues with training the network - loss stays high around 0.69 the entire training time HOT 1
- Question about "info.txt" and "interest.txt" - test db HOT 1
- training HOT 1
- MatchNet: Keras implementation
- Link to Original patch data not working
- could you provide the pretained network with the bottleneck layer of dimension 128, 256.
- Could you provide the training prototxt file? HOT 1
- how to fine-tune or retrain matchnet? HOT 6
- Error occurred when I had the expect result, Error rate at 95% recall: 4.48% HOT 2
- Access denied for pretrained models and datasets HOT 5
- You have removed it from your website .how can i download the dataset ? HOT 5
- how to make the dataset for tensorflow HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
š 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. ššš
-
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 ā¤ļø Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from matchnet.