Hfrxdjt

Why would five hundred and five same as one?

Friend wants my recommendation but I don't want to give it to him

categorizing a variable turns it from insignificant to significant

Should I be concerned about student access to a test bank?

Why can't I get pgrep output right to variable on bash script?

Did I make a mistake by ccing email to boss to others?

Why is indicated airspeed rather than ground speed used during the takeoff roll?

Output visual diagram of picture

How do you justify more code being written by following clean code practices?

Checking @@ROWCOUNT failing

Are all namekians brothers?

Extract substring according to regexp with sed or grep

Highest stage count that are used one right after the other?

Derivative of an interpolated function

Center page as a whole without centering each element individually

Offset in split text content

How do I prevent inappropriate ads from appearing in my game?

What is the period/term used describe Giuseppe Arcimboldo's style of painting?

How can I, as DM, avoid the Conga Line of Death occurring when implementing some form of flanking rule?

Not hide and seek

Error in master's thesis, I do not know what to do

What is it called when someone votes for an option that's not their first choice?

How would a solely written language work mechanically

How to split IPA spelling into syllables

Why loss and val_loss vary for same value of lr, epoch, batch size and lr-decay?

Keras difference beetween val_loss and loss during trainingLSTM Timeseries recursive prediction converge to same valueKeras intuition/guidelines for setting epochs and batch sizeWhy might a neural network consistently underestimate its target?Why is my Keras model not learning image segmentation?Bidirectional GRU: validation loss stuck on plateau diverges from well performing training losscustom loss in keras, problem with batch sizeGeting batch size in keras custom losspredict gives the same output value for every image (Keras)InvalidArgumentError: Conv2DCustomBackpropInput: input and out_backprop must have the same batch size

0

$begingroup$

I am training a deep neural network in Keras. I have set the values of learning rate, learning rate decay, epochs and batch size.

(I am using fit_generator i.e data coming from a generator but without any kind of shuffling.)

Being said that my training shows highly differenttraining summary.

Sometimes it's like:

And other times it is

The two of the above images show the highly unpredictable behavior of model for the same values of all hyperparameters.

Can someone explain why this is happening?

keras predictive-modeling

share|improve this question

edited 43 secs ago

yamini goel

asked 33 mins ago

yamini goelyamini goel

214

$endgroup$

add a comment | 

0

$begingroup$

I am training a deep neural network in Keras. I have set the values of learning rate, learning rate decay, epochs and batch size.

(I am using fit_generator i.e data coming from a generator but without any kind of shuffling.)

Being said that my training shows highly differenttraining summary.

Sometimes it's like:

And other times it is

The two of the above images show the highly unpredictable behavior of model for the same values of all hyperparameters.

Can someone explain why this is happening?

keras predictive-modeling

share|improve this question

edited 43 secs ago

yamini goel

asked 33 mins ago

yamini goelyamini goel

214

$endgroup$

add a comment | 

$begingroup$

I am training a deep neural network in Keras. I have set the values of learning rate, learning rate decay, epochs and batch size.

(I am using fit_generator i.e data coming from a generator but without any kind of shuffling.)

Being said that my training shows highly differenttraining summary.

Sometimes it's like:

And other times it is

The two of the above images show the highly unpredictable behavior of model for the same values of all hyperparameters.

Can someone explain why this is happening?

keras predictive-modeling

share|improve this question

edited 43 secs ago

yamini goel

asked 33 mins ago

yamini goelyamini goel

214

$endgroup$

share|improve this question

edited 43 secs ago

yamini goel

asked 33 mins ago

yamini goelyamini goel

214

share|improve this question

edited 43 secs ago

yamini goel

asked 33 mins ago

yamini goelyamini goel

214

asked 33 mins ago

yamini goelyamini goel

214

asked 33 mins ago

yamini goelyamini goel

214