python - how loss and metric are calculated in cntk -


i new cntk , python. have created python program based on trainresnet_cifar10.py train 4736 of (64x64x3) images , test 2180 images 4 classes. after train 160 epochs, got loss = 0.663 , metric = 29.37%. finished evaluation metric = 18.94%. when evaluate train model based on cntklibrarycsevalexamples.cs test 2180 images, 2180 classified 1 class (second class). questions are:

  1. i assume loss calculated cross_entropy_with_softmax(z, label_var) , metric using classification_error(z, label_var). correct , how determined?
  2. what mean of metric = 29.37% , evaluation metric = 18.94%? train , test images, respectively?
  3. what cause totally wrong evaluate results?

any appreciated.

(1) yes.

(2) 29.37% mean 29.37% of classification correct. evaluation on test data, assuming reading both training , test data.

(3) make sure input same format, mean normalize or subtract mean in python, if need same in c#. can run eval first using python , see result get?


Comments

Post a Comment

Popular posts from this blog

android - InAppBilling registering BroadcastReceiver in AndroidManifest -

i'm implementing inapp billing in android app. works well, however, i'm trying decouple broadcast receiver activity manifest. suggestion in android's trivialdrive sample: // important: dynamically register broadcast messages updated purchases. // register receiver here instead of <receiver> in manifest // because call getpurchases() @ startup, therefore can ignore // broadcasts sent while app isn't running. // note: registering listener in activity bad idea, done here // because sample. regardless, receiver must registered after // iabhelper setup, before first call getpurchases(). currently there's class extends broadcastreceiver : public class iabbroadcastreceiver extends broadcastreceiver { /** * intent action receiver should filter for. */ public static final string action = "com.android.vending.billing.purchases_updated"; private final iabbroadcastlistener mlistener; public iabbroadcastreceiver(iabbroadcastlistener listener) { m...
Read more

python Tkinter Capturing keyboard events save as one single string -

is possible store keyboard events 1 string? code below stores 1 char , prints it. card reader or bar code reader, contains collection of character/ string not 1 character @ time. goal save char pressed text variable. from tkinter import * root = tk() def key(event): text= event.char text+= event.char print ("pressed", text) def callback(event): frame.focus_set() print ("clicked at", event.x, event.y) frame = frame(root, width=100, height=100) frame.bind("<key>", key) frame.bind("<button-1>", callback) frame.pack() root.mainloop() currently, creating text variable , everytime key() function gets called, , text stores last character typed. you can define text module level variable , , use module level text inside key function - text = '' def key(event): global text text+= event.char print("pressed", text)
Read more

sql server - Why does Linq-to-SQL add unnecessary COUNT()? -

here tables: create table customer ( cid int primary key, name varchar(32) ) create table ord ( oid int primary key, cid int foreign key references customer, address varchar(20) ) here's linq-to-sql statement: var aaa = c in db.customer select new { c, o = c.ord.tolist() }; and here's inexplicable query generated linq-to-sql: select [t0].[cid] [cid], [t0].[name] [name], [t1].[oid] [oid], [t1].[cid] [cid2], [t1].[address] [address], (select count(*) [dbo].[ord] [t2] [t2].[cid] = [t0].[cid]) [value] [dbo].[customer] [t0] left outer join [dbo].[ord] [t1] on [t1].[cid] = [t0].[cid] order [t0].[cid], [t1].[oid] i want understand how rid of count(*) part. it's entirely uncalled for! linq needs count(*) in order determine number of entries returned o = c.ord.tolist() .
Read more