Tensorflow, movie reviews predict
0
I am trying to make the following tutorial: https://www.tensorflow.org/tutorials/keras/basic_text_classification
train_data = keras.preprocessing.sequence.pad_sequences(train_data,
value=word_index["<PAD>"],
padding='post',
maxlen=256)
test_data = keras.preprocessing.sequence.pad_sequences(test_data,
value=word_index["<PAD>"],
padding='post',
maxlen=256)
vocab_size = 10000
model = keras.Sequential()
model.add(keras.layers.Embedding(vocab_size, 16))
model.add(keras.layers.GlobalAveragePooling1D())
model.add(keras.layers.Dense(16, activation=tf.nn.relu))
model.add(keras.layers.Dense(1, activation=tf.nn.sigmoid))
model.summary()
model.compile(optimizer=tf.train.AdamOptimizer(),
loss='binary_crossentropy',
metrics=['accuracy'])
prediction = model.predict(test_data[5])
print(prediction)
Why does the prediction return an array of 256? And not 0 or 1? How to do ?
Thank you in advance.
tensorflow keras
asked Nov 14 '18 at 21:35
calypso59calypso59
11
add a comment |
0
I am trying to make the following tutorial: https://www.tensorflow.org/tutorials/keras/basic_text_classification
train_data = keras.preprocessing.sequence.pad_sequences(train_data,
value=word_index["<PAD>"],
padding='post',
maxlen=256)
test_data = keras.preprocessing.sequence.pad_sequences(test_data,
value=word_index["<PAD>"],
padding='post',
maxlen=256)
vocab_size = 10000
model = keras.Sequential()
model.add(keras.layers.Embedding(vocab_size, 16))
model.add(keras.layers.GlobalAveragePooling1D())
model.add(keras.layers.Dense(16, activation=tf.nn.relu))
model.add(keras.layers.Dense(1, activation=tf.nn.sigmoid))
model.summary()
model.compile(optimizer=tf.train.AdamOptimizer(),
loss='binary_crossentropy',
metrics=['accuracy'])
prediction = model.predict(test_data[5])
print(prediction)
Why does the prediction return an array of 256? And not 0 or 1? How to do ?
Thank you in advance.
tensorflow keras
asked Nov 14 '18 at 21:35
calypso59calypso59
11
1
Are you using the same train and test data as the tutorial? Can you share your model summary?
– rachelim
Nov 15 '18 at 7:32
add a comment |
0
0
0
I am trying to make the following tutorial: https://www.tensorflow.org/tutorials/keras/basic_text_classification
train_data = keras.preprocessing.sequence.pad_sequences(train_data,
value=word_index["<PAD>"],
padding='post',
maxlen=256)
test_data = keras.preprocessing.sequence.pad_sequences(test_data,
value=word_index["<PAD>"],
padding='post',
maxlen=256)
vocab_size = 10000
model = keras.Sequential()
model.add(keras.layers.Embedding(vocab_size, 16))
model.add(keras.layers.GlobalAveragePooling1D())
model.add(keras.layers.Dense(16, activation=tf.nn.relu))
model.add(keras.layers.Dense(1, activation=tf.nn.sigmoid))
model.summary()
model.compile(optimizer=tf.train.AdamOptimizer(),
loss='binary_crossentropy',
metrics=['accuracy'])
prediction = model.predict(test_data[5])
print(prediction)
Why does the prediction return an array of 256? And not 0 or 1? How to do ?
Thank you in advance.
tensorflow keras
asked Nov 14 '18 at 21:35
calypso59calypso59
11
I am trying to make the following tutorial: https://www.tensorflow.org/tutorials/keras/basic_text_classification
train_data = keras.preprocessing.sequence.pad_sequences(train_data,
value=word_index["<PAD>"],
padding='post',
maxlen=256)
test_data = keras.preprocessing.sequence.pad_sequences(test_data,
value=word_index["<PAD>"],
padding='post',
maxlen=256)
vocab_size = 10000
model = keras.Sequential()
model.add(keras.layers.Embedding(vocab_size, 16))
model.add(keras.layers.GlobalAveragePooling1D())
model.add(keras.layers.Dense(16, activation=tf.nn.relu))
model.add(keras.layers.Dense(1, activation=tf.nn.sigmoid))
model.summary()
model.compile(optimizer=tf.train.AdamOptimizer(),
loss='binary_crossentropy',
metrics=['accuracy'])
prediction = model.predict(test_data[5])
print(prediction)
Why does the prediction return an array of 256? And not 0 or 1? How to do ?
Thank you in advance.
tensorflow keras
tensorflow keras
asked Nov 14 '18 at 21:35
calypso59calypso59
11
asked Nov 14 '18 at 21:35
calypso59calypso59
11
asked Nov 14 '18 at 21:35
calypso59calypso59
11
asked Nov 14 '18 at 21:35
calypso59calypso59
11
asked Nov 14 '18 at 21:35
calypso59calypso59
11
11
1
Are you using the same train and test data as the tutorial? Can you share your model summary?
– rachelim
Nov 15 '18 at 7:32
add a comment |
1
Are you using the same train and test data as the tutorial? Can you share your model summary?
– rachelim
Nov 15 '18 at 7:32
1
1
Are you using the same train and test data as the tutorial? Can you share your model summary?
– rachelim
Nov 15 '18 at 7:32
Are you using the same train and test data as the tutorial? Can you share your model summary?
– rachelim
Nov 15 '18 at 7:32
add a comment |
1 Answer
1
active
oldest
votes
0
you should try to pass list of numpy arrays, as far as I remember
Try something like:
model.predict(np.array([test_data[5]]))
Does it what you expected?
Hope this helps!
answered Nov 14 '18 at 22:32
Yaroslav BigusYaroslav Bigus
480520
Thank you for your reply. Unfortunately it does not work (same return)
– calypso59
Nov 14 '18 at 22:55
my bad, try to pass numpy array model.predict(np.array([test_data[5]])) should works, also don't forget to call model.fit to train your model :)
– Yaroslav Bigus
Nov 15 '18 at 8:12
@calypso59 does updated code helps you?
– Yaroslav Bigus
Nov 19 '18 at 10:58
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
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53309074%2ftensorflow-movie-reviews-predict%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
0
you should try to pass list of numpy arrays, as far as I remember
Try something like:
model.predict(np.array([test_data[5]]))
Does it what you expected?
Hope this helps!
answered Nov 14 '18 at 22:32
Yaroslav BigusYaroslav Bigus
480520
Thank you for your reply. Unfortunately it does not work (same return)
– calypso59
Nov 14 '18 at 22:55
my bad, try to pass numpy array model.predict(np.array([test_data[5]])) should works, also don't forget to call model.fit to train your model :)
– Yaroslav Bigus
Nov 15 '18 at 8:12
@calypso59 does updated code helps you?
– Yaroslav Bigus
Nov 19 '18 at 10:58
add a comment |
0
you should try to pass list of numpy arrays, as far as I remember
Try something like:
model.predict(np.array([test_data[5]]))
Does it what you expected?
Hope this helps!
answered Nov 14 '18 at 22:32
Yaroslav BigusYaroslav Bigus
480520
Thank you for your reply. Unfortunately it does not work (same return)
– calypso59
Nov 14 '18 at 22:55
my bad, try to pass numpy array model.predict(np.array([test_data[5]])) should works, also don't forget to call model.fit to train your model :)
– Yaroslav Bigus
Nov 15 '18 at 8:12
@calypso59 does updated code helps you?
– Yaroslav Bigus
Nov 19 '18 at 10:58
add a comment |
0
0
0
you should try to pass list of numpy arrays, as far as I remember
Try something like:
model.predict(np.array([test_data[5]]))
Does it what you expected?
Hope this helps!
answered Nov 14 '18 at 22:32
Yaroslav BigusYaroslav Bigus
480520
you should try to pass list of numpy arrays, as far as I remember
Try something like:
model.predict(np.array([test_data[5]]))
Does it what you expected?
Hope this helps!
answered Nov 14 '18 at 22:32
Yaroslav BigusYaroslav Bigus
480520
edited Nov 15 '18 at 8:13
answered Nov 14 '18 at 22:32
Yaroslav BigusYaroslav Bigus
480520
answered Nov 14 '18 at 22:32
Yaroslav BigusYaroslav Bigus
480520
answered Nov 14 '18 at 22:32
Yaroslav BigusYaroslav Bigus
480520
480520
Thank you for your reply. Unfortunately it does not work (same return)
– calypso59
Nov 14 '18 at 22:55
my bad, try to pass numpy array model.predict(np.array([test_data[5]])) should works, also don't forget to call model.fit to train your model :)
– Yaroslav Bigus
Nov 15 '18 at 8:12
@calypso59 does updated code helps you?
– Yaroslav Bigus
Nov 19 '18 at 10:58
add a comment |
Thank you for your reply. Unfortunately it does not work (same return)
– calypso59
Nov 14 '18 at 22:55
my bad, try to pass numpy array model.predict(np.array([test_data[5]])) should works, also don't forget to call model.fit to train your model :)
– Yaroslav Bigus
Nov 15 '18 at 8:12
@calypso59 does updated code helps you?
– Yaroslav Bigus
Nov 19 '18 at 10:58
Thank you for your reply. Unfortunately it does not work (same return)
– calypso59
Nov 14 '18 at 22:55
Thank you for your reply. Unfortunately it does not work (same return)
– calypso59
Nov 14 '18 at 22:55
my bad, try to pass numpy array model.predict(np.array([test_data[5]])) should works, also don't forget to call model.fit to train your model :)
– Yaroslav Bigus
Nov 15 '18 at 8:12
my bad, try to pass numpy array model.predict(np.array([test_data[5]])) should works, also don't forget to call model.fit to train your model :)
– Yaroslav Bigus
Nov 15 '18 at 8:12
@calypso59 does updated code helps you?
– Yaroslav Bigus
Nov 19 '18 at 10:58
@calypso59 does updated code helps you?
– Yaroslav Bigus
Nov 19 '18 at 10:58
add a comment |
draft saved
draft discarded
Thanks for contributing an answer to Stack Overflow!
- 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.
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%2fstackoverflow.com%2fquestions%2f53309074%2ftensorflow-movie-reviews-predict%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
1
Are you using the same train and test data as the tutorial? Can you share your model summary?
– rachelim
Nov 15 '18 at 7:32