machine learning - How do you add new categories and training to a pretrained Inception v3 model in TensorFlow? -


i'm trying utilize pre-trained model inception v3 (trained on 2012 imagenet data set) , expand in several missing categories.

i have tensorflow built source cuda on ubuntu 14.04, , examples transfer learning on flowers working great. however, flowers example strips away final layer , removes 1,000 existing categories, means can identify 5 species of flowers, can no longer identify pandas, example. https://www.tensorflow.org/versions/r0.8/how_tos/image_retraining/index.html

how can add 5 flower categories existing 1,000 categories imagenet (and add training 5 new flower categories) have 1,005 categories test image can classified as? in other words, able identify both pandas , sunflowers?

i understand 1 option download entire imagenet training set , flowers example set , train scratch, given current computing power, take long time, , wouldn't allow me add, say, 100 more categories down line.

one idea had set parameter fine_tune false when retraining 5 flower categories final layer not stripped: https://github.com/tensorflow/models/blob/master/inception/readme.md#how-to-retrain-a-trained-model-on-the-flowers-data , i'm not sure how proceed, , not sure if result in valid model 1,005 categories. thoughts.

unfortunately, cannot add categories existing graph; you'll have save checkpoint , train graph checkpoint onward.


-

Comments

Post a Comment

Popular posts from this blog

scala - 'wrong top statement declaration' when using slick in IntelliJ -

Image
i'm porting project scala 2.9 2.10, therefore have use slick instead of scalaquery. i'm using slick 2.1.0 since supports ms access. according this tutorial , upgrade guide changed robs object class , added val robs : why error message wrong top statement declaration , how rid of it? edit: i'm new scala... according this question seems can't put val outside of methods or classes, right? code above directly in packge. right approach slick then? should move code in class or trait? according this changed val robs = tablequery[robs] to object robs extends tablequery(new robs(_)) {} . no warnings or errors anymore. :)
Read more

c# - DevExpress.Wpf.Grid.InfiniteGridSizeException was unhandled -

Image
when using devexpress, see error: devexpress.wpf.grid.infinitegridsizeexception unhandled message="by default, infinite grid height not allowed since grid rows rendered , hence grid work slowly. fix issue, should place grid container give finite height grid, or should manually specify grid's height or maxheight. note can avoid exception setting gridcontrol.allowinfinitegridsize static property true, in case grid run slowly." the problem dxgrid has infinite height. to fix, set height non-infinite. snoop absolutely invaluable this: if "height" xaml element infinite (i.e. 0 or nan ), can set using one of following: option 1: height="{binding path=actualheight, relativesource={relativesource mode=findancestor, ancestortype=uielement}}" option 2: verticalalignment="stretch" option 3: height="auto" hint: use verticalalignment="stretch" if child of grid <rowdefinition height=
Read more

PySide and Qt Properties: Connecting signals from Python to QML -

i trying run simple pyside appliccation design made in qml. call function in qml python in separated thread. i have following qml view: import qt 4.7 rectangle { visible: true width: 100; height: 100 color: "lightgrey" text { id: datestr objectname: "datestr" x: 10 y: 10 text: "init text" font.pixelsize: 12 function updatedata(text) { datestr.text = qstr(text) console.log("you said: " + text) } } } here application: some imports.... #!/usr/bin/python import sys import time pyside import qtdeclarative, qtcore pyside.qtgui import qapplication pyside.qtdeclarative import qdeclarativeview the qthread worker.... #worker thread class worker(qtcore.qthread): updateprogress = qtcore.signal(int) def __init__(self, child): qtcore.qthread.__init__(self) self.child = child def run(self):
Read more