Comments (6)
Thinking more about it, it makes sense train error could also be affected if we are modifying the params (LR, bias etc) adaptively based on the val error (which is really great!).
Still, the train error on first iteration is much higher with "eval = val" (0.76) vs. "eval = train" (0.61)?
from cxxnet.
Do you use CUDNN? I find there is some unstable stuff in CUDNN pooling, which makes unpredictable result. Now I disabled CuDNN pooling.
from cxxnet.
No, I don't use CUDNN. I'm planning to run the exact same model in both master and v2-refac and see if my submission scores in the competition are any different. Will update with what I find.
from cxxnet.
Ok, something's definitely amiss. I ran the exact same bowl.conf and pred.conf files (just minor chnages to be rev compatible) in both master and v2-refactor. My train error / val error in Master was .227 / .257 and in V2-refac was .342 / .296.
When I submitted in Kaggle, leaderboard score for master was 0.90 and V2-refac was 0.98. This was only one single submission with no averaging of multiple outputs. Something definitely seems off with using v2-refac or I'm missing some details?
FYI, this is the older master from ~6 weeks back, I haven't updated at all.
from cxxnet.
Thanks very much! I will check my configuration tomorrow. If possible, could you share me your configuration? just email me: antinucleon àt gmail.com so that I will be more clear of what happened. I used V2 for all competition, and I didn't find out any abnormal.
from cxxnet.
I re-run the experiment again. result is:
new:
[312] train-error:0.237291 train-logloss:0.712367 val-error:0.232272 val-logloss:0.725718
old:
[312] train-error:0.244916 train-logloss:0.745804 val-error:0.241366 val-logloss:0.7564
So I don't think it is CXXNET's problem.
from cxxnet.
Related Issues (20)
- "invalid model format" when doing predict
- Is the memory something wrong?
- Memory leak run with MSHADOW_DIST_PS?
- Can you give me the config of GoogLeNet?
- Configure question about activtionlayer and split layer HOT 2
- cudnn_convolution_layer : Is it cost a lost of temp memory? HOT 2
- ImageNet Example : train error does not decrease! HOT 23
- Train ImageNet on Windows Server, the error rate dose not decrease HOT 3
- why the const kDataKeyStep equals 4? HOT 5
- Implemetation of #GoogLeNet BN + prelu using #cxxnet?
- compile error on "undefined reference to `google::LogMessage::" HOT 7
- DMAR fault after shuffle the image_list in ImageNet
- problems when training ImageNet HOT 1
- cuDNN failed HOT 1
- cifar10 CNN训练问题 HOT 2
- CNN 训练问题
- CNN样本组织
- CXXNet model to Caffe model conversion HOT 1
- CXXnet build.sh error no matching function for call to ‘unpack_patch2col HOT 1
- error
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 cxxnet.