Ufdjrw

PIC mathematical operations weird problem

Expansion//Explosion and Siren Stormtamer

What *exactly* is electrical current, voltage, and resistance?

finding a tangent line to a parabola

A faster way to compute the largest prime factor

Additive group of local rings

Co-worker works way more than he should

How to open locks without disable device?

Are all CP/M-80 implementations binary compatible?

How to avoid introduction cliches

What ability score does a Hexblade's Pact Weapon use for attack and damage when wielded by another character?

Is Electric Central Heating worth it if using Solar Panels?

Would reducing the reference voltage of an ADC have any effect on accuracy?

Why did Israel vote against lifting the American embargo on Cuba?

Is accepting an invalid credit card number a security issue?

Seek and ye shall find

What is the least dense liquid under normal conditions?

Why did C use the -> operator instead of reusing the . operator?

Does Feeblemind produce an ongoing magical effect that can be dispelled?

Arriving in Atlanta after US Preclearance in Dublin. Will I go through TSA security in Atlanta to transfer to a connecting flight?

Contradiction proof for inequality of P and NP?

My admission is revoked after accepting the admission offer

Is there any hidden 'W' sound after 'comment' in : Comment est-elle?

Married in secret, can marital status in passport be changed at a later date?

How to find the wrong predictions in Keras?

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty height:90px;width:728px;box-sizing:border-box;

0

I have built a Keras model for extracting information from a raw input of text input. I am getting an accuracy of 0.9869. How can I know which of the training data is making the accuracy go low? I have pasted the code I am using below.

import numpy as np 
from keras.models import Model, load_model
from keras.layers import Input, Dense, LSTM, Activation, Bidirectional, Dot, Flatten
from keras.callbacks import ModelCheckpoint

x_nyha = np.load("data/x_nyha.npy")
y_nyha = np.load("data/y/y_nyha.npy")
print(x_nyha.shape)
print(y_nyha.shape)


input_shape = x_nyha.shape[1:3]

X = Input(shape=input_shape)
A = Bidirectional(LSTM(512, return_sequences=True), merge_mode='concat')(X)
D = Dense(900, activation='relu')(A)
E = Dense(1, activation='sigmoid')(D)
Y = Flatten()(E)
model = Model(X, Y)
model.summary()

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])


batch_size = 128
num_epochs = 50


model.fit(x_nyha, y_nyha, batch_size=batch_size, epochs=num_epochs, verbose=1)

python-3.x machine-learning keras classification

share|improve this question

edited Mar 9 at 14:02

desertnaut

21.2k84680

asked Mar 9 at 6:30

Geeth Govind SGeeth Govind S

156

add a comment | 

0

I have built a Keras model for extracting information from a raw input of text input. I am getting an accuracy of 0.9869. How can I know which of the training data is making the accuracy go low? I have pasted the code I am using below.

import numpy as np 
from keras.models import Model, load_model
from keras.layers import Input, Dense, LSTM, Activation, Bidirectional, Dot, Flatten
from keras.callbacks import ModelCheckpoint

x_nyha = np.load("data/x_nyha.npy")
y_nyha = np.load("data/y/y_nyha.npy")
print(x_nyha.shape)
print(y_nyha.shape)


input_shape = x_nyha.shape[1:3]

X = Input(shape=input_shape)
A = Bidirectional(LSTM(512, return_sequences=True), merge_mode='concat')(X)
D = Dense(900, activation='relu')(A)
E = Dense(1, activation='sigmoid')(D)
Y = Flatten()(E)
model = Model(X, Y)
model.summary()

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])


batch_size = 128
num_epochs = 50


model.fit(x_nyha, y_nyha, batch_size=batch_size, epochs=num_epochs, verbose=1)

python-3.x machine-learning keras classification

share|improve this question

edited Mar 9 at 14:02

desertnaut

21.2k84680

asked Mar 9 at 6:30

Geeth Govind SGeeth Govind S

156

add a comment | 

I have built a Keras model for extracting information from a raw input of text input. I am getting an accuracy of 0.9869. How can I know which of the training data is making the accuracy go low? I have pasted the code I am using below.

import numpy as np 
from keras.models import Model, load_model
from keras.layers import Input, Dense, LSTM, Activation, Bidirectional, Dot, Flatten
from keras.callbacks import ModelCheckpoint

x_nyha = np.load("data/x_nyha.npy")
y_nyha = np.load("data/y/y_nyha.npy")
print(x_nyha.shape)
print(y_nyha.shape)


input_shape = x_nyha.shape[1:3]

X = Input(shape=input_shape)
A = Bidirectional(LSTM(512, return_sequences=True), merge_mode='concat')(X)
D = Dense(900, activation='relu')(A)
E = Dense(1, activation='sigmoid')(D)
Y = Flatten()(E)
model = Model(X, Y)
model.summary()

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])


batch_size = 128
num_epochs = 50


model.fit(x_nyha, y_nyha, batch_size=batch_size, epochs=num_epochs, verbose=1)

python-3.x machine-learning keras classification

share|improve this question

edited Mar 9 at 14:02

desertnaut

21.2k84680

asked Mar 9 at 6:30

Geeth Govind SGeeth Govind S

156

import numpy as np 
from keras.models import Model, load_model
from keras.layers import Input, Dense, LSTM, Activation, Bidirectional, Dot, Flatten
from keras.callbacks import ModelCheckpoint

x_nyha = np.load("data/x_nyha.npy")
y_nyha = np.load("data/y/y_nyha.npy")
print(x_nyha.shape)
print(y_nyha.shape)


input_shape = x_nyha.shape[1:3]

X = Input(shape=input_shape)
A = Bidirectional(LSTM(512, return_sequences=True), merge_mode='concat')(X)
D = Dense(900, activation='relu')(A)
E = Dense(1, activation='sigmoid')(D)
Y = Flatten()(E)
model = Model(X, Y)
model.summary()

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])


batch_size = 128
num_epochs = 50


model.fit(x_nyha, y_nyha, batch_size=batch_size, epochs=num_epochs, verbose=1)

share|improve this question

edited Mar 9 at 14:02

desertnaut

21.2k84680

asked Mar 9 at 6:30

Geeth Govind SGeeth Govind S

156

share|improve this question

edited Mar 9 at 14:02

desertnaut

21.2k84680

asked Mar 9 at 6:30

Geeth Govind SGeeth Govind S

156

edited Mar 9 at 14:02

desertnaut

21.2k84680

edited Mar 9 at 14:02

desertnaut

21.2k84680

asked Mar 9 at 6:30

Geeth Govind SGeeth Govind S

156

asked Mar 9 at 6:30

Geeth Govind SGeeth Govind S

156

1 Answer
1

active

oldest

votes

2

I think that the easiest way will be the following: train model on training data, make predictions on training data and have a look at training samples where predictions are wrong.

An example of code:

model.fit(x_nyha, y_nyha, batch_size=batch_size, epochs=num_epochs, verbose=1)
prediction = np.round(model.predict(x_nyha))
wrong_predictions = x_nyha[prediction != y_nyha]

This way wrong_predictions contains rows, where your prediction as wrong.

share|improve this answer

answered Mar 9 at 6:39

Andrey LukyanenkoAndrey Lukyanenko

1,5692612

• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  
  Thank you. I checked it out and it worked.
  
  – Geeth Govind S
  Mar 10 at 4:44
  

  
  
  
  

add a comment | 

Your Answer

StackExchange.ifUsing("editor", function ()
StackExchange.using("externalEditor", function ()
StackExchange.using("snippets", function ()
StackExchange.snippets.init();
);
);
, "code-snippets");

StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "1"
;
initTagRenderer("".split(" "), "".split(" "), channelOptions);

StackExchange.using("externalEditor", function()
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled)
StackExchange.using("snippets", function()
createEditor();
);

else
createEditor();

);

function createEditor()
StackExchange.prepareEditor(
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader:
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);



);

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);

Sign up using Google

Sign up using Facebook

Sign up using Email and Password

Post as a guest

Name

Email

Required, but never shown

StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f55074681%2fhow-to-find-the-wrong-predictions-in-keras%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

2

I think that the easiest way will be the following: train model on training data, make predictions on training data and have a look at training samples where predictions are wrong.

An example of code:

model.fit(x_nyha, y_nyha, batch_size=batch_size, epochs=num_epochs, verbose=1)
prediction = np.round(model.predict(x_nyha))
wrong_predictions = x_nyha[prediction != y_nyha]

This way wrong_predictions contains rows, where your prediction as wrong.

share|improve this answer

answered Mar 9 at 6:39

Andrey LukyanenkoAndrey Lukyanenko

1,5692612

• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  
  Thank you. I checked it out and it worked.
  
  – Geeth Govind S
  Mar 10 at 4:44
  

  
  
  
  

add a comment | 

2

I think that the easiest way will be the following: train model on training data, make predictions on training data and have a look at training samples where predictions are wrong.

An example of code:

model.fit(x_nyha, y_nyha, batch_size=batch_size, epochs=num_epochs, verbose=1)
prediction = np.round(model.predict(x_nyha))
wrong_predictions = x_nyha[prediction != y_nyha]

This way wrong_predictions contains rows, where your prediction as wrong.

share|improve this answer

answered Mar 9 at 6:39

Andrey LukyanenkoAndrey Lukyanenko

1,5692612

• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  
  Thank you. I checked it out and it worked.
  
  – Geeth Govind S
  Mar 10 at 4:44
  

  
  
  
  

add a comment | 

I think that the easiest way will be the following: train model on training data, make predictions on training data and have a look at training samples where predictions are wrong.

An example of code:

model.fit(x_nyha, y_nyha, batch_size=batch_size, epochs=num_epochs, verbose=1)
prediction = np.round(model.predict(x_nyha))
wrong_predictions = x_nyha[prediction != y_nyha]

This way wrong_predictions contains rows, where your prediction as wrong.

share|improve this answer

answered Mar 9 at 6:39

Andrey LukyanenkoAndrey Lukyanenko

1,5692612

model.fit(x_nyha, y_nyha, batch_size=batch_size, epochs=num_epochs, verbose=1)
prediction = np.round(model.predict(x_nyha))
wrong_predictions = x_nyha[prediction != y_nyha]

share|improve this answer

answered Mar 9 at 6:39

Andrey LukyanenkoAndrey Lukyanenko

1,5692612

answered Mar 9 at 6:39

Andrey LukyanenkoAndrey Lukyanenko

1,5692612

answered Mar 9 at 6:39

Andrey LukyanenkoAndrey Lukyanenko

1,5692612