Best Practice for Tensorflow Keras validation
0
$begingroup$
I'm a newbie for ML and it might be that I've made a mistake, but it seems that I'm getting quite different results from different ways. My code is like this:
from sklearn.model_selection import KFold,
import tensorflow as tf
from tensorflow.keras import layers
X, y = some_func_to_get_data()
model = tf.keras.Sequential()
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dropout(0.1))
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dropout(0.1))
model.add(layers.Dense(1, activation='relu'))
model.compile(optimizer=tf.train.AdamOptimizer(0.001), loss='mse', metrics=['mse'])
then, the first way to get validation:
model.fit(X, y, validation_split=0.1, epochs=30, batch_size=32)
and the output for last epoch is somewhat like:
Epoch 30/30
4029/4029 [==============================] - 0s 16us/step - loss: 0.1289 - mean_squared_error: 0.1289 - val_loss: 0.2312 - val_mean_squared_error: 0.2312
the second way is to do K-Fold cross validation myself:
crossvalidation = KFold(n_splits=10, shuffle=False, random_state=1)
for train, test in crossvalidation.split(X, y):
model.fit(X[train], y[train], epochs=30, batch_size=32, verbose=0)
scores = model.evaluate(X[test], y[test], verbose=0)
print(scores)
and the output:
[0.11302296231899943, 0.11302296231899943]
[0.1082031112164259, 0.1082031112164259]
[0.15109882104609693, 0.15109882104609693]
[0.11689347002123084, 0.11689347002123084]
[0.0495243084483913, 0.0495243084483913]
[0.09257462301424571, 0.09257462301424571]
[0.1153098890291793, 0.1153098890291793]
[0.11075845470764493, 0.11075845470764493]
[0.09127715530011478, 0.09127715530011478]
[0.05938179766388414, 0.05938179766388414]
The problem is, why the value given in the second way much smaller than val_loss in the first way? Are they using different metrics or anything?
keras tensorflow cross-validation
asked 2 mins ago
jjsjjs
1
New contributor
jjs is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
0
$begingroup$
I'm a newbie for ML and it might be that I've made a mistake, but it seems that I'm getting quite different results from different ways. My code is like this:
from sklearn.model_selection import KFold,
import tensorflow as tf
from tensorflow.keras import layers
X, y = some_func_to_get_data()
model = tf.keras.Sequential()
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dropout(0.1))
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dropout(0.1))
model.add(layers.Dense(1, activation='relu'))
model.compile(optimizer=tf.train.AdamOptimizer(0.001), loss='mse', metrics=['mse'])
then, the first way to get validation:
model.fit(X, y, validation_split=0.1, epochs=30, batch_size=32)
and the output for last epoch is somewhat like:
Epoch 30/30
4029/4029 [==============================] - 0s 16us/step - loss: 0.1289 - mean_squared_error: 0.1289 - val_loss: 0.2312 - val_mean_squared_error: 0.2312
the second way is to do K-Fold cross validation myself:
crossvalidation = KFold(n_splits=10, shuffle=False, random_state=1)
for train, test in crossvalidation.split(X, y):
model.fit(X[train], y[train], epochs=30, batch_size=32, verbose=0)
scores = model.evaluate(X[test], y[test], verbose=0)
print(scores)
and the output:
[0.11302296231899943, 0.11302296231899943]
[0.1082031112164259, 0.1082031112164259]
[0.15109882104609693, 0.15109882104609693]
[0.11689347002123084, 0.11689347002123084]
[0.0495243084483913, 0.0495243084483913]
[0.09257462301424571, 0.09257462301424571]
[0.1153098890291793, 0.1153098890291793]
[0.11075845470764493, 0.11075845470764493]
[0.09127715530011478, 0.09127715530011478]
[0.05938179766388414, 0.05938179766388414]
The problem is, why the value given in the second way much smaller than val_loss in the first way? Are they using different metrics or anything?
keras tensorflow cross-validation
asked 2 mins ago
jjsjjs
1
New contributor
jjs is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
0
0
0
$begingroup$
I'm a newbie for ML and it might be that I've made a mistake, but it seems that I'm getting quite different results from different ways. My code is like this:
from sklearn.model_selection import KFold,
import tensorflow as tf
from tensorflow.keras import layers
X, y = some_func_to_get_data()
model = tf.keras.Sequential()
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dropout(0.1))
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dropout(0.1))
model.add(layers.Dense(1, activation='relu'))
model.compile(optimizer=tf.train.AdamOptimizer(0.001), loss='mse', metrics=['mse'])
then, the first way to get validation:
model.fit(X, y, validation_split=0.1, epochs=30, batch_size=32)
and the output for last epoch is somewhat like:
Epoch 30/30
4029/4029 [==============================] - 0s 16us/step - loss: 0.1289 - mean_squared_error: 0.1289 - val_loss: 0.2312 - val_mean_squared_error: 0.2312
the second way is to do K-Fold cross validation myself:
crossvalidation = KFold(n_splits=10, shuffle=False, random_state=1)
for train, test in crossvalidation.split(X, y):
model.fit(X[train], y[train], epochs=30, batch_size=32, verbose=0)
scores = model.evaluate(X[test], y[test], verbose=0)
print(scores)
and the output:
[0.11302296231899943, 0.11302296231899943]
[0.1082031112164259, 0.1082031112164259]
[0.15109882104609693, 0.15109882104609693]
[0.11689347002123084, 0.11689347002123084]
[0.0495243084483913, 0.0495243084483913]
[0.09257462301424571, 0.09257462301424571]
[0.1153098890291793, 0.1153098890291793]
[0.11075845470764493, 0.11075845470764493]
[0.09127715530011478, 0.09127715530011478]
[0.05938179766388414, 0.05938179766388414]
The problem is, why the value given in the second way much smaller than val_loss in the first way? Are they using different metrics or anything?
keras tensorflow cross-validation
asked 2 mins ago
jjsjjs
1
New contributor
jjs is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
I'm a newbie for ML and it might be that I've made a mistake, but it seems that I'm getting quite different results from different ways. My code is like this:
from sklearn.model_selection import KFold,
import tensorflow as tf
from tensorflow.keras import layers
X, y = some_func_to_get_data()
model = tf.keras.Sequential()
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dropout(0.1))
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dropout(0.1))
model.add(layers.Dense(1, activation='relu'))
model.compile(optimizer=tf.train.AdamOptimizer(0.001), loss='mse', metrics=['mse'])
then, the first way to get validation:
model.fit(X, y, validation_split=0.1, epochs=30, batch_size=32)
and the output for last epoch is somewhat like:
Epoch 30/30
4029/4029 [==============================] - 0s 16us/step - loss: 0.1289 - mean_squared_error: 0.1289 - val_loss: 0.2312 - val_mean_squared_error: 0.2312
the second way is to do K-Fold cross validation myself:
crossvalidation = KFold(n_splits=10, shuffle=False, random_state=1)
for train, test in crossvalidation.split(X, y):
model.fit(X[train], y[train], epochs=30, batch_size=32, verbose=0)
scores = model.evaluate(X[test], y[test], verbose=0)
print(scores)
and the output:
[0.11302296231899943, 0.11302296231899943]
[0.1082031112164259, 0.1082031112164259]
[0.15109882104609693, 0.15109882104609693]
[0.11689347002123084, 0.11689347002123084]
[0.0495243084483913, 0.0495243084483913]
[0.09257462301424571, 0.09257462301424571]
[0.1153098890291793, 0.1153098890291793]
[0.11075845470764493, 0.11075845470764493]
[0.09127715530011478, 0.09127715530011478]
[0.05938179766388414, 0.05938179766388414]
The problem is, why the value given in the second way much smaller than val_loss in the first way? Are they using different metrics or anything?
keras tensorflow cross-validation
keras tensorflow cross-validation
asked 2 mins ago
jjsjjs
1
New contributor
jjs is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 2 mins ago
jjsjjs
1
New contributor
jjs is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 2 mins ago
jjsjjs
1
New contributor
jjs is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 2 mins ago
jjsjjs
1
asked 2 mins ago
jjsjjs
1
1
New contributor
jjs is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
New contributor
jjs is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
jjs is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
add a comment |
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function () {
return StackExchange.using("mathjaxEditing", function () {
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
});
});
}, "mathjax-editing");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "557"
};
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: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
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
});
}
});
jjs is a new contributor. Be nice, and check out our Code of Conduct.
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
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f44541%2fbest-practice-for-tensorflow-keras-validation%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
jjs is a new contributor. Be nice, and check out our Code of Conduct.
draft saved
draft discarded
jjs is a new contributor. Be nice, and check out our Code of Conduct.
jjs is a new contributor. Be nice, and check out our Code of Conduct.
jjs is a new contributor. Be nice, and check out our Code of Conduct.
Thanks for contributing an answer to Data Science Stack Exchange!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
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
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f44541%2fbest-practice-for-tensorflow-keras-validation%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
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
Required, but never shown
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
Required, but never shown
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
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
