deep-learning


Should I scale the ground truth images in semantic segmentation?


I am applying CNNs for semantic segmentation. I am hoping someone here can recommend. What I am doing now is that I scaled ground truth images. I have 5 classes that I scaled them to (0-1) in Data Layer based on this:
transform_param {
scale: 0.00390625
}
I am wondering whether I am wrong or right? Is this scaling value correct?
whenever I am not adding `
it is showing the following error:
[...]
I0510 23:21:28.086776 9072 solver.cpp:397] Test net output #0: accuracy = 0
I0510 23:21:28.086812 9072 solver.cpp:397] Test net output #1: loss = 1.9416 (* 1 = 1.9416 loss)
F0510 23:21:28.150539 9072 math_functions.cu:141] Check failed: status == CUBLAS_STATUS_SUCCESS (11 vs. 0) CUBLAS_STATUS_MAPPING_ERROR
*** Check failure stack trace: ***
# 0x7fb9d4e7f5cd google::LogMessage::Fail()
# 0x7fb9d4e81433 google::LogMessage::SendToLog()
# 0x7fb9d4e7f15b google::LogMessage::Flush()
# 0x7fb9d4e81e1e google::LogMessageFatal::~LogMessageFatal()
# 0x7fb9d56665ea caffe::caffe_gpu_asum<>()
# 0x7fb9d5633a38 caffe::SoftmaxWithLossLayer<>::Forward_gpu()
# 0x7fb9d54bde41 caffe::Net<>::ForwardFromTo()
# 0x7fb9d54bdf47 caffe::Net<>::Forward()
# 0x7fb9d54e8d28 caffe::Solver<>::Step()
# 0x7fb9d54e98ca caffe::Solver<>::Solve()
# 0x40acd4 train()
# 0x407418 main
# 0x7fb9d360f830 __libc_start_main
# 0x407ce9 _start
# (nil) (unknown)

Related Links

How to set KDD dataset as input of autoencoder in Keras
Linking libraries error while installing Caffe:
How to perform multi labeling classification (for CNN)?
compile pytorch with ICC (intel c++ compiler)
How to remove layers by name from .prototxt in caffe using Python
transfer of learning between ANNs
Benchmarking an autoencoder
How to punish illegal output in sequence labeling?
Fine-Tuning CNN Model for Auto-Encoding
NaN in lasagne Siamese Network while using resNet model
How to prevent converge to mean solution for regression problems in CNN?
Output tensors to a Model must be Keras tensors
How can I trace the loss of a custom regularization term during training in Keras?
Divide training and testing for caffe to reduce memory usage
Is this graphical visualization correct?
Deconvolution Layer does not accept 5D blobs with bilinear filler

Categories

HOME
embedded
c++11
amp-html
google-spreadsheet
datastore
flex
static
serialization
hessian
access
rom
switch-statement
pyqt4
computer-science
octave
alamofire
datastage
event-sourcing
nodemcu
connector
enterprise-miner
articulate-storyline
squashfs
inno-download-plugin
tosca
moses
android-sharedpreferences
corpus
rpgle
ntp
send
dst
mockjax
activexobject
ideascript
recurrent-neural-network
news
vmware-fusion
linqpad
phpdbg
fclose
trojan
corruption
d3-force-directed
slackware
usart
angular2-testing
winusb
greatest-n-per-group
vorpal.js
avspeechsynthesizer
shopping
android-wake-lock
qiime
dbamp
database-relations
grgit
zen-cart
wso2greg
ansi
exceldatareader
apache-spark-1.3
android-cookiemanager
entry-point
human-computer-interface
mdichild
winginx
ray
high-resolution
bin
ie8-compatibility-mode
scrypt
jeromq
ice-cube
poker
facebook-timeline
actiondispatch
argouml
monotouch.dialog
sentestingkit
fitbounds
stress
convention
rmdir
cac
resharper-6.0
jqueryform
drupal-fivestar
aspmenu
pos-for-.net
cldc
great-circle

Resources

Mobile Apps Dev
Database Users
javascript
java
csharp
php
android
MS Developer
developer works
python
ios
c
html
jquery
RDBMS discuss
Cloud Virtualization
Database Dev&Adm
javascript
java
csharp
php
python
android
jquery
ruby
ios
html
Mobile App
Mobile App
Mobile App