Having trouble with CNN prediction
I am using Convolutional Neural Networking for vehicle identification, my first time. Currently, I am working with just 2 classes(bike and car). Training set: 420 car images and 825 bike images. Test set: 44 car images and 110 bike images Car and Bike images are in different format(bmp,jpg). In single prediction, I am always getting 'bike'. I have tried using the Sigmoid function in the output layer. Then I get only 'car'. My code is like following: ``
from keras.models import Sequential
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense,Dropout
classifier = Sequential()
classifier.add(Conv2D(32, (3, 3), input_shape = (128, 128, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (3, 3)))
# Adding a second convolutional layer
classifier.add(Conv2D(32, (3, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (3, 3)))
# Step 3 - Flattening
classifier.add(Flatten())
# Step 4 - Full connection
classifier.add(Dropout(0.3))
classifier.add(Dense(units = 128, activation = 'relu'))
classifier.add(Dense(units = 1, activation = 'sigmoid'))
# Compiling the CNN
classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
# Part 2 - Fitting the CNN to the images
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale = 1./255,
shear_range = 0.2,
zoom_range = 0.2,
rotation_range= 3,
fill_mode = 'nearest',
horizontal_flip = True)
test_datagen = ImageDataGenerator(rescale = 1./255,
shear_range = 0.2,
zoom_range = 0.2,
rotation_range= 3,
fill_mode = 'nearest',
horizontal_flip = True)
training_set = train_datagen.flow_from_directory('dataset/training_set',
target_size = (128, 128),
batch_size = 10,
class_mode = 'binary')
test_set = test_datagen.flow_from_directory('dataset/test_set',
target_size = (128, 128),
batch_size = 10,
class_mode = 'binary')
classifier.fit_generator(training_set,
steps_per_epoch = 1092//10,
epochs = 3,
validation_data = test_set,
validation_steps = 20)
classifier.save("car_bike.h5")
And I wanted to test a single image like the following:
test_image = image.load_img('dataset/single_prediction/download (3).jpg', target_size = (128, 128))
test_image = image.img_to_array(test_image)
test_image *= (1/255.0)
test_image = np.expand_dims(test_image, axis = 0)
result = classifier.predict(test_image)
if result[0][0] == 1:
prediction = 'bike'
else:
prediction = 'car'
print(" {}".format(prediction))
python keras deep-learning
add a comment |
I am using Convolutional Neural Networking for vehicle identification, my first time. Currently, I am working with just 2 classes(bike and car). Training set: 420 car images and 825 bike images. Test set: 44 car images and 110 bike images Car and Bike images are in different format(bmp,jpg). In single prediction, I am always getting 'bike'. I have tried using the Sigmoid function in the output layer. Then I get only 'car'. My code is like following: ``
from keras.models import Sequential
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense,Dropout
classifier = Sequential()
classifier.add(Conv2D(32, (3, 3), input_shape = (128, 128, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (3, 3)))
# Adding a second convolutional layer
classifier.add(Conv2D(32, (3, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (3, 3)))
# Step 3 - Flattening
classifier.add(Flatten())
# Step 4 - Full connection
classifier.add(Dropout(0.3))
classifier.add(Dense(units = 128, activation = 'relu'))
classifier.add(Dense(units = 1, activation = 'sigmoid'))
# Compiling the CNN
classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
# Part 2 - Fitting the CNN to the images
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale = 1./255,
shear_range = 0.2,
zoom_range = 0.2,
rotation_range= 3,
fill_mode = 'nearest',
horizontal_flip = True)
test_datagen = ImageDataGenerator(rescale = 1./255,
shear_range = 0.2,
zoom_range = 0.2,
rotation_range= 3,
fill_mode = 'nearest',
horizontal_flip = True)
training_set = train_datagen.flow_from_directory('dataset/training_set',
target_size = (128, 128),
batch_size = 10,
class_mode = 'binary')
test_set = test_datagen.flow_from_directory('dataset/test_set',
target_size = (128, 128),
batch_size = 10,
class_mode = 'binary')
classifier.fit_generator(training_set,
steps_per_epoch = 1092//10,
epochs = 3,
validation_data = test_set,
validation_steps = 20)
classifier.save("car_bike.h5")
And I wanted to test a single image like the following:
test_image = image.load_img('dataset/single_prediction/download (3).jpg', target_size = (128, 128))
test_image = image.img_to_array(test_image)
test_image *= (1/255.0)
test_image = np.expand_dims(test_image, axis = 0)
result = classifier.predict(test_image)
if result[0][0] == 1:
prediction = 'bike'
else:
prediction = 'car'
print(" {}".format(prediction))
python keras deep-learning
add a comment |
I am using Convolutional Neural Networking for vehicle identification, my first time. Currently, I am working with just 2 classes(bike and car). Training set: 420 car images and 825 bike images. Test set: 44 car images and 110 bike images Car and Bike images are in different format(bmp,jpg). In single prediction, I am always getting 'bike'. I have tried using the Sigmoid function in the output layer. Then I get only 'car'. My code is like following: ``
from keras.models import Sequential
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense,Dropout
classifier = Sequential()
classifier.add(Conv2D(32, (3, 3), input_shape = (128, 128, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (3, 3)))
# Adding a second convolutional layer
classifier.add(Conv2D(32, (3, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (3, 3)))
# Step 3 - Flattening
classifier.add(Flatten())
# Step 4 - Full connection
classifier.add(Dropout(0.3))
classifier.add(Dense(units = 128, activation = 'relu'))
classifier.add(Dense(units = 1, activation = 'sigmoid'))
# Compiling the CNN
classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
# Part 2 - Fitting the CNN to the images
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale = 1./255,
shear_range = 0.2,
zoom_range = 0.2,
rotation_range= 3,
fill_mode = 'nearest',
horizontal_flip = True)
test_datagen = ImageDataGenerator(rescale = 1./255,
shear_range = 0.2,
zoom_range = 0.2,
rotation_range= 3,
fill_mode = 'nearest',
horizontal_flip = True)
training_set = train_datagen.flow_from_directory('dataset/training_set',
target_size = (128, 128),
batch_size = 10,
class_mode = 'binary')
test_set = test_datagen.flow_from_directory('dataset/test_set',
target_size = (128, 128),
batch_size = 10,
class_mode = 'binary')
classifier.fit_generator(training_set,
steps_per_epoch = 1092//10,
epochs = 3,
validation_data = test_set,
validation_steps = 20)
classifier.save("car_bike.h5")
And I wanted to test a single image like the following:
test_image = image.load_img('dataset/single_prediction/download (3).jpg', target_size = (128, 128))
test_image = image.img_to_array(test_image)
test_image *= (1/255.0)
test_image = np.expand_dims(test_image, axis = 0)
result = classifier.predict(test_image)
if result[0][0] == 1:
prediction = 'bike'
else:
prediction = 'car'
print(" {}".format(prediction))
python keras deep-learning
I am using Convolutional Neural Networking for vehicle identification, my first time. Currently, I am working with just 2 classes(bike and car). Training set: 420 car images and 825 bike images. Test set: 44 car images and 110 bike images Car and Bike images are in different format(bmp,jpg). In single prediction, I am always getting 'bike'. I have tried using the Sigmoid function in the output layer. Then I get only 'car'. My code is like following: ``
from keras.models import Sequential
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense,Dropout
classifier = Sequential()
classifier.add(Conv2D(32, (3, 3), input_shape = (128, 128, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (3, 3)))
# Adding a second convolutional layer
classifier.add(Conv2D(32, (3, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (3, 3)))
# Step 3 - Flattening
classifier.add(Flatten())
# Step 4 - Full connection
classifier.add(Dropout(0.3))
classifier.add(Dense(units = 128, activation = 'relu'))
classifier.add(Dense(units = 1, activation = 'sigmoid'))
# Compiling the CNN
classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
# Part 2 - Fitting the CNN to the images
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale = 1./255,
shear_range = 0.2,
zoom_range = 0.2,
rotation_range= 3,
fill_mode = 'nearest',
horizontal_flip = True)
test_datagen = ImageDataGenerator(rescale = 1./255,
shear_range = 0.2,
zoom_range = 0.2,
rotation_range= 3,
fill_mode = 'nearest',
horizontal_flip = True)
training_set = train_datagen.flow_from_directory('dataset/training_set',
target_size = (128, 128),
batch_size = 10,
class_mode = 'binary')
test_set = test_datagen.flow_from_directory('dataset/test_set',
target_size = (128, 128),
batch_size = 10,
class_mode = 'binary')
classifier.fit_generator(training_set,
steps_per_epoch = 1092//10,
epochs = 3,
validation_data = test_set,
validation_steps = 20)
classifier.save("car_bike.h5")
And I wanted to test a single image like the following:
test_image = image.load_img('dataset/single_prediction/download (3).jpg', target_size = (128, 128))
test_image = image.img_to_array(test_image)
test_image *= (1/255.0)
test_image = np.expand_dims(test_image, axis = 0)
result = classifier.predict(test_image)
if result[0][0] == 1:
prediction = 'bike'
else:
prediction = 'car'
print(" {}".format(prediction))
python keras deep-learning
python keras deep-learning
asked Nov 13 '18 at 4:24
Iftekhar JamilIftekhar Jamil
1
1
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
If you print your result
matrix you'll see that it doesn't have only 1s and 0s but floats between these numbers. You may pick a threshold and set values that exceed it to 1 and everything else to 0.
thanks for your response. You are right I am getting float numbers in the result matrix. But its value is never close to 1. For 'car' I am getting around 0.0003 and for bike it is <1e-10. So even I set a threshold of 0.5 it's not going to be 1.
– Iftekhar Jamil
Nov 13 '18 at 6:16
np.argmax would only work for 'categorized_crossentropy' loss function, so forget about that since you use 'binary_crossentropy'. I suggest increasing number of epochs from 3 to 100 or more and seeing the results again. Also make sure you have equal or close number of samples for cars and bikes. -editing my answer to get rid of argmax part-
– Mete Han Kahraman
Nov 13 '18 at 8:34
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
});
}
});
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%2f53273786%2fhaving-trouble-with-cnn-prediction%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
If you print your result
matrix you'll see that it doesn't have only 1s and 0s but floats between these numbers. You may pick a threshold and set values that exceed it to 1 and everything else to 0.
thanks for your response. You are right I am getting float numbers in the result matrix. But its value is never close to 1. For 'car' I am getting around 0.0003 and for bike it is <1e-10. So even I set a threshold of 0.5 it's not going to be 1.
– Iftekhar Jamil
Nov 13 '18 at 6:16
np.argmax would only work for 'categorized_crossentropy' loss function, so forget about that since you use 'binary_crossentropy'. I suggest increasing number of epochs from 3 to 100 or more and seeing the results again. Also make sure you have equal or close number of samples for cars and bikes. -editing my answer to get rid of argmax part-
– Mete Han Kahraman
Nov 13 '18 at 8:34
add a comment |
If you print your result
matrix you'll see that it doesn't have only 1s and 0s but floats between these numbers. You may pick a threshold and set values that exceed it to 1 and everything else to 0.
thanks for your response. You are right I am getting float numbers in the result matrix. But its value is never close to 1. For 'car' I am getting around 0.0003 and for bike it is <1e-10. So even I set a threshold of 0.5 it's not going to be 1.
– Iftekhar Jamil
Nov 13 '18 at 6:16
np.argmax would only work for 'categorized_crossentropy' loss function, so forget about that since you use 'binary_crossentropy'. I suggest increasing number of epochs from 3 to 100 or more and seeing the results again. Also make sure you have equal or close number of samples for cars and bikes. -editing my answer to get rid of argmax part-
– Mete Han Kahraman
Nov 13 '18 at 8:34
add a comment |
If you print your result
matrix you'll see that it doesn't have only 1s and 0s but floats between these numbers. You may pick a threshold and set values that exceed it to 1 and everything else to 0.
If you print your result
matrix you'll see that it doesn't have only 1s and 0s but floats between these numbers. You may pick a threshold and set values that exceed it to 1 and everything else to 0.
edited Nov 13 '18 at 8:34
answered Nov 13 '18 at 5:33
Mete Han KahramanMete Han Kahraman
40017
40017
thanks for your response. You are right I am getting float numbers in the result matrix. But its value is never close to 1. For 'car' I am getting around 0.0003 and for bike it is <1e-10. So even I set a threshold of 0.5 it's not going to be 1.
– Iftekhar Jamil
Nov 13 '18 at 6:16
np.argmax would only work for 'categorized_crossentropy' loss function, so forget about that since you use 'binary_crossentropy'. I suggest increasing number of epochs from 3 to 100 or more and seeing the results again. Also make sure you have equal or close number of samples for cars and bikes. -editing my answer to get rid of argmax part-
– Mete Han Kahraman
Nov 13 '18 at 8:34
add a comment |
thanks for your response. You are right I am getting float numbers in the result matrix. But its value is never close to 1. For 'car' I am getting around 0.0003 and for bike it is <1e-10. So even I set a threshold of 0.5 it's not going to be 1.
– Iftekhar Jamil
Nov 13 '18 at 6:16
np.argmax would only work for 'categorized_crossentropy' loss function, so forget about that since you use 'binary_crossentropy'. I suggest increasing number of epochs from 3 to 100 or more and seeing the results again. Also make sure you have equal or close number of samples for cars and bikes. -editing my answer to get rid of argmax part-
– Mete Han Kahraman
Nov 13 '18 at 8:34
thanks for your response. You are right I am getting float numbers in the result matrix. But its value is never close to 1. For 'car' I am getting around 0.0003 and for bike it is <1e-10. So even I set a threshold of 0.5 it's not going to be 1.
– Iftekhar Jamil
Nov 13 '18 at 6:16
thanks for your response. You are right I am getting float numbers in the result matrix. But its value is never close to 1. For 'car' I am getting around 0.0003 and for bike it is <1e-10. So even I set a threshold of 0.5 it's not going to be 1.
– Iftekhar Jamil
Nov 13 '18 at 6:16
np.argmax would only work for 'categorized_crossentropy' loss function, so forget about that since you use 'binary_crossentropy'. I suggest increasing number of epochs from 3 to 100 or more and seeing the results again. Also make sure you have equal or close number of samples for cars and bikes. -editing my answer to get rid of argmax part-
– Mete Han Kahraman
Nov 13 '18 at 8:34
np.argmax would only work for 'categorized_crossentropy' loss function, so forget about that since you use 'binary_crossentropy'. I suggest increasing number of epochs from 3 to 100 or more and seeing the results again. Also make sure you have equal or close number of samples for cars and bikes. -editing my answer to get rid of argmax part-
– Mete Han Kahraman
Nov 13 '18 at 8:34
add a comment |
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.
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%2f53273786%2fhaving-trouble-with-cnn-prediction%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