deep learning - Output from fully connected network in tensorflow - 


weights = {  # 5x5 conv, 1 input, 32 outputs  'wc1': tf.variable(tf.random_normal([5, 5, 1, 32])), `# 5x5 conv, 32 inputs, 64 outputs`  'wc2': tf.variable(tf.random_normal([5, 5, 32, 64])),   # connected, 7*7*64 inputs, 1024 outputs 'wd1': tf.variable(tf.random_normal([7*7*64, 1024])),   # 1024 inputs, 10 outputs (class prediction)    'out': tf.variable(tf.random_normal([1024, n_classes]))    }

in code,the output connected layer given 1024 cannot understand calculation '1024' generated , cannot find satisfactory answer tensorflow documentation.and how ouput size affects prediction result. in advance.

a number 1024 empirical, depending on data , goal.

in general, think question has many ramifications answer succinctly. i'll answer in restricted , assumed context of question: convolutional nets. kind of network describe have hidden layers more nodes target number of classes (this classifier, right?).

in case last hidden layer has 1024 nodes, more 10 output classes. necessary number? depends on data quantity, diversity, etc. number not mean without context , goal.

the least can confident with: number higher output classes. doing so, network able store "large" number of features describe classes. output layer gets these many features input, , computes combinations down expected number of classes.


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